Vulnerability-Lookup

CVE-2026-107295 (GCVE-0-2026-107295)

Vulnerability from cvelistv5 – Published: 2026-10-08 17:02 – Updated: 2026-10-08 17:53

Title

`pydantic-ai-slim` web UI `/api/chat` accepts browser-simple cross-origin requests that can trigger agent tool execution

Summary

Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.34.0 until 1.107.4 and 2.28.0, the Agent.to_web() and clai web development chat endpoint has missing request content-type validation. A website visited by a developer can submit a browser-compatible request to a loopback-hosted chat server, causing the served agent to run and execute tools with the privileges and credentials of the local process; client-relayed approval decisions also leave requires_approval=True tools exposed. Binding to localhost does not prevent a browser page from reaching the loopback address. This issue is fixed in versions 1.107.4 and 2.28.0.

Severity

7.6 (High)


                        
                          CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L

SSVC

Exploitation: none Automatable: no Technical Impact: partial

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-10-08 17:53 UTC

CWE

CWE-352 - Cross-Site Request Forgery (CSRF)

Assigner

GitHub_M CNA under the mitre root

CNA scorecard C 72/100 over 7580 records in the last 180 days details

References

7 references

URL	Tags
https://github.com/pydantic/pydantic-ai/security/…	x_refsource_CONFIRM
https://github.com/pydantic/pydantic-ai/pull/7382	x_refsource_MISC
https://github.com/pydantic/pydantic-ai/pull/7383	x_refsource_MISC
https://github.com/pydantic/pydantic-ai/commit/d2…	x_refsource_MISC
https://github.com/pydantic/pydantic-ai/commit/dd…	x_refsource_MISC
https://github.com/pydantic/pydantic-ai/releases/…	x_refsource_MISC
https://github.com/pydantic/pydantic-ai/releases/…	x_refsource_MISC

Impacted products

2 products

Vendor	Product	Version	CPE status
pydantic	pydantic-ai	Affected: >= 1.34.0, < 1.107.4 Affected: >= 2.0.0b1, < 2.28.0	guessed
pydantic	pydantic-ai-slim	Affected: >= 1.34.0, < 1.107.4 Affected: >= 2.0.0b1, < 2.28.0	guessed

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-107295",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-10-08T17:53:16.989703Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-10-08T17:53:29.464Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "pydantic-ai",
          "vendor": "pydantic",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 1.34.0, \u003c 1.107.4"
            },
            {
              "status": "affected",
              "version": "\u003e= 2.0.0b1, \u003c 2.28.0"
            }
          ]
        },
        {
          "product": "pydantic-ai-slim",
          "vendor": "pydantic",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 1.34.0, \u003c 1.107.4"
            },
            {
              "status": "affected",
              "version": "\u003e= 2.0.0b1, \u003c 2.28.0"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.34.0 until 1.107.4 and 2.28.0, the Agent.to_web() and clai web development chat endpoint has missing request content-type validation. A website visited by a developer can submit a browser-compatible request to a loopback-hosted chat server, causing the served agent to run and execute tools with the privileges and credentials of the local process; client-relayed approval decisions also leave requires_approval=True tools exposed. Binding to localhost does not prevent a browser page from reaching the loopback address. This issue is fixed in versions 1.107.4 and 2.28.0."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "LOW",
            "baseScore": 7.6,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "LOW",
            "integrityImpact": "HIGH",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-352",
              "description": "CWE-352: Cross-Site Request Forgery (CSRF)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-10-08T17:02:36.718Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-h4xc-3qfq-jf93",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-h4xc-3qfq-jf93"
        },
        {
          "name": "https://github.com/pydantic/pydantic-ai/pull/7382",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/pydantic/pydantic-ai/pull/7382"
        },
        {
          "name": "https://github.com/pydantic/pydantic-ai/pull/7383",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/pydantic/pydantic-ai/pull/7383"
        },
        {
          "name": "https://github.com/pydantic/pydantic-ai/commit/d2690201a1834005d382dbf5c47e0ed94ef8bf46",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/pydantic/pydantic-ai/commit/d2690201a1834005d382dbf5c47e0ed94ef8bf46"
        },
        {
          "name": "https://github.com/pydantic/pydantic-ai/commit/dd2abbdfa029c9ad138e7cc0edd2eaeaf9ed69c0",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/pydantic/pydantic-ai/commit/dd2abbdfa029c9ad138e7cc0edd2eaeaf9ed69c0"
        },
        {
          "name": "https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.4",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.4"
        },
        {
          "name": "https://github.com/pydantic/pydantic-ai/releases/tag/v2.28.0",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/pydantic/pydantic-ai/releases/tag/v2.28.0"
        }
      ],
      "source": {
        "advisory": "GHSA-h4xc-3qfq-jf93",
        "discovery": "UNKNOWN"
      },
      "title": "`pydantic-ai-slim` web UI `/api/chat` accepts browser-simple cross-origin requests that can trigger agent tool execution"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-107295",
    "datePublished": "2026-10-08T17:02:36.718Z",
    "dateReserved": "2026-10-07T15:53:23.587Z",
    "dateUpdated": "2026-10-08T17:53:29.464Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "nvd": {
      "cve": {
        "affected": [
          {
            "affectedData": [
              {
                "product": "pydantic-ai",
                "vendor": "pydantic",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003e= 1.34.0, \u003c 1.107.4"
                  },
                  {
                    "status": "affected",
                    "version": "\u003e= 2.0.0b1, \u003c 2.28.0"
                  }
                ]
              },
              {
                "product": "pydantic-ai-slim",
                "vendor": "pydantic",
                "versions": [
                  {
                    "status": "affected",
                    "version": "\u003e= 1.34.0, \u003c 1.107.4"
                  },
                  {
                    "status": "affected",
                    "version": "\u003e= 2.0.0b1, \u003c 2.28.0"
                  }
                ]
              }
            ],
            "source": "security-advisories@github.com"
          }
        ],
        "cveTags": [],
        "descriptions": [
          {
            "lang": "en",
            "value": "Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.34.0 until 1.107.4 and 2.28.0, the Agent.to_web() and clai web development chat endpoint has missing request content-type validation. A website visited by a developer can submit a browser-compatible request to a loopback-hosted chat server, causing the served agent to run and execute tools with the privileges and credentials of the local process; client-relayed approval decisions also leave requires_approval=True tools exposed. Binding to localhost does not prevent a browser page from reaching the loopback address. This issue is fixed in versions 1.107.4 and 2.28.0."
          }
        ],
        "id": "CVE-2026-107295",
        "lastModified": "2026-10-08T20:35:31.200",
        "metrics": {
          "cvssMetricV31": [
            {
              "cvssData": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "LOW",
                "baseScore": 7.6,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "LOW",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "REQUIRED",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L",
                "version": "3.1"
              },
              "exploitabilityScore": 2.8,
              "impactScore": 4.7,
              "source": "security-advisories@github.com",
              "type": "Secondary"
            }
          ],
          "ssvcV203": [
            {
              "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "ssvcData": {
                "id": "CVE-2026-107295",
                "options": [
                  {
                    "exploitation": "none"
                  },
                  {
                    "automatable": "no"
                  },
                  {
                    "technicalImpact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-10-08T17:53:16.989703Z",
                "version": "2.0.3"
              }
            }
          ]
        },
        "published": "2026-10-08T17:17:15.237",
        "references": [
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/pydantic/pydantic-ai/commit/d2690201a1834005d382dbf5c47e0ed94ef8bf46"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/pydantic/pydantic-ai/commit/dd2abbdfa029c9ad138e7cc0edd2eaeaf9ed69c0"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/pydantic/pydantic-ai/pull/7382"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/pydantic/pydantic-ai/pull/7383"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.4"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/pydantic/pydantic-ai/releases/tag/v2.28.0"
          },
          {
            "source": "security-advisories@github.com",
            "url": "https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-h4xc-3qfq-jf93"
          }
        ],
        "sourceIdentifier": "security-advisories@github.com",
        "vulnStatus": "Awaiting Analysis",
        "weaknesses": [
          {
            "description": [
              {
                "lang": "en",
                "value": "CWE-352"
              }
            ],
            "source": "security-advisories@github.com",
            "type": "Secondary"
          }
        ]
      }
    },
    "redhat_vex": {
      "aggregate_severity": "Important",
      "current_release_date": "2026-10-08T22:16:30+00:00",
      "cve": "CVE-2026-107295",
      "id": "CVE-2026-107295",
      "initial_release_date": "2026-10-08T17:02:36.718000+00:00",
      "product_status:known_affected": "1",
      "source": "Red Hat CSAF VEX",
      "status": "final",
      "title": "pydantic-ai-slim: pydantic-ai-slim: Unauthorized tool execution via missing Content-Type validation",
      "url": "https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-107295.json",
      "version": "3"
    },
    "vulnrichment": {
      "containers": {
        "adp": [
          {
            "metrics": [
              {
                "other": {
                  "content": {
                    "id": "CVE-2026-107295",
                    "options": [
                      {
                        "Exploitation": "none"
                      },
                      {
                        "Automatable": "no"
                      },
                      {
                        "Technical Impact": "partial"
                      }
                    ],
                    "role": "CISA Coordinator",
                    "timestamp": "2026-10-08T17:53:16.989703Z",
                    "version": "2.0.3"
                  },
                  "type": "ssvc"
                }
              }
            ],
            "providerMetadata": {
              "dateUpdated": "2026-10-08T17:53:23.662Z",
              "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
              "shortName": "CISA-ADP"
            },
            "title": "CISA ADP Vulnrichment"
          }
        ],
        "cna": {
          "affected": [
            {
              "product": "pydantic-ai",
              "vendor": "pydantic",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 1.34.0, \u003c 1.107.4"
                },
                {
                  "status": "affected",
                  "version": "\u003e= 2.0.0b1, \u003c 2.28.0"
                }
              ]
            },
            {
              "product": "pydantic-ai-slim",
              "vendor": "pydantic",
              "versions": [
                {
                  "status": "affected",
                  "version": "\u003e= 1.34.0, \u003c 1.107.4"
                },
                {
                  "status": "affected",
                  "version": "\u003e= 2.0.0b1, \u003c 2.28.0"
                }
              ]
            }
          ],
          "descriptions": [
            {
              "lang": "en",
              "value": "Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.34.0 until 1.107.4 and 2.28.0, the Agent.to_web() and clai web development chat endpoint has missing request content-type validation. A website visited by a developer can submit a browser-compatible request to a loopback-hosted chat server, causing the served agent to run and execute tools with the privileges and credentials of the local process; client-relayed approval decisions also leave requires_approval=True tools exposed. Binding to localhost does not prevent a browser page from reaching the loopback address. This issue is fixed in versions 1.107.4 and 2.28.0."
            }
          ],
          "metrics": [
            {
              "cvssV3_1": {
                "attackComplexity": "LOW",
                "attackVector": "NETWORK",
                "availabilityImpact": "LOW",
                "baseScore": 7.6,
                "baseSeverity": "HIGH",
                "confidentialityImpact": "LOW",
                "integrityImpact": "HIGH",
                "privilegesRequired": "NONE",
                "scope": "UNCHANGED",
                "userInteraction": "REQUIRED",
                "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L",
                "version": "3.1"
              }
            }
          ],
          "problemTypes": [
            {
              "descriptions": [
                {
                  "cweId": "CWE-352",
                  "description": "CWE-352: Cross-Site Request Forgery (CSRF)",
                  "lang": "en",
                  "type": "CWE"
                }
              ]
            }
          ],
          "providerMetadata": {
            "dateUpdated": "2026-10-08T17:02:36.718Z",
            "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
            "shortName": "GitHub_M"
          },
          "references": [
            {
              "name": "https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-h4xc-3qfq-jf93",
              "tags": [
                "x_refsource_CONFIRM"
              ],
              "url": "https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-h4xc-3qfq-jf93"
            },
            {
              "name": "https://github.com/pydantic/pydantic-ai/pull/7382",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/pydantic/pydantic-ai/pull/7382"
            },
            {
              "name": "https://github.com/pydantic/pydantic-ai/pull/7383",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/pydantic/pydantic-ai/pull/7383"
            },
            {
              "name": "https://github.com/pydantic/pydantic-ai/commit/d2690201a1834005d382dbf5c47e0ed94ef8bf46",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/pydantic/pydantic-ai/commit/d2690201a1834005d382dbf5c47e0ed94ef8bf46"
            },
            {
              "name": "https://github.com/pydantic/pydantic-ai/commit/dd2abbdfa029c9ad138e7cc0edd2eaeaf9ed69c0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/pydantic/pydantic-ai/commit/dd2abbdfa029c9ad138e7cc0edd2eaeaf9ed69c0"
            },
            {
              "name": "https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.4",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.4"
            },
            {
              "name": "https://github.com/pydantic/pydantic-ai/releases/tag/v2.28.0",
              "tags": [
                "x_refsource_MISC"
              ],
              "url": "https://github.com/pydantic/pydantic-ai/releases/tag/v2.28.0"
            }
          ],
          "source": {
            "advisory": "GHSA-h4xc-3qfq-jf93",
            "discovery": "UNKNOWN"
          },
          "title": "`pydantic-ai-slim` web UI `/api/chat` accepts browser-simple cross-origin requests that can trigger agent tool execution"
        }
      },
      "cveMetadata": {
        "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "assignerShortName": "GitHub_M",
        "cveId": "CVE-2026-107295",
        "datePublished": "2026-10-08T17:02:36.718Z",
        "dateReserved": "2026-10-07T15:53:23.587Z",
        "dateUpdated": "2026-10-08T17:53:29.464Z",
        "state": "PUBLISHED"
      },
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}

BREW-OTERM-CVE-2026-107295 (GHSA-H4XC-3QFQ-JF93)

Vulnerability from osv_homebrew – Published: 2026-10-08 18:40 – Updated: 2026-10-08 18:40 – Source website

Summary

Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): a website visited by the developer can trigger agent runs and server-side tool execution on the local chat endpoint

Details

Summary

The Pydantic AI development web chat UI (Agent.to_web(), clai web) did not check the content type of requests to its chat endpoint. This allowed a website visited by a developer to submit a request to a chat UI running on that developer's machine, causing the served agent to run and to execute its tools with the privileges and credentials of the local process.

Binding the web UI to localhost — the default — does not prevent this, because a page open in the developer's browser can reach the loopback address.

Impact

Applications and developers serving an agent through Agent.to_web() or clai web. The consequences depend on the tools the served agent exposes, and can include data disclosure as well as unwanted tool side effects. Tools marked requires_approval=True were not protected either, because the endpoint trusts approval decisions relayed by the client.

Mitigation

Upgrade to a patched version. The chat endpoint now requires Content-Type: application/json and rejects other requests before the request body is parsed and before the agent runs. The bundled chat UI already sends this header; scripts and other non-browser clients that call the endpoint directly may need to be updated to send it.

If you cannot upgrade, don't run the web UI while browsing untrusted sites, stop it when you aren't using it, and don't serve an agent with side-effecting tools through it.

Credits

Thai Son Dinh from VinSOC Labs (R&D)

Severity

7.6 (High)


                    
                      CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L

References

URL

Type

	https://github.com/pydantic/pydantic-ai/security/…	WEB
	https://github.com/pydantic/pydantic-ai/pull/7382	WEB
	https://github.com/pydantic/pydantic-ai/pull/7383	WEB
	https://github.com/pydantic/pydantic-ai/commit/d2…	WEB
	https://github.com/pydantic/pydantic-ai/commit/dd…	WEB
	https://github.com/pydantic/pydantic-ai	PACKAGE
	https://github.com/pydantic/pydantic-ai/releases/…	WEB
	https://github.com/pydantic/pydantic-ai/releases/…	WEB

JSON

To clipboard

{
  "affected": [
    {
      "ecosystem_specific": {
        "fix": "bump",
        "range_state": "fixed",
        "resource": "pydantic-ai-slim",
        "resource_purl": "pkg:pypi/pydantic-ai-slim@2.51.0",
        "upstream_fixed_in": "2.28.0"
      },
      "package": {
        "ecosystem": "Homebrew",
        "name": "oterm",
        "purl": "pkg:brew/oterm"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0.15.0"
            },
            {
              "fixed": "0.24.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "database_specific": {
    "confidence": "high",
    "source": "matched",
    "strategy": "registry",
    "upstream_evidence": [
      {
        "ecosystem": "PyPI",
        "key": "pkg:pypi/pydantic-ai-slim@2.51.0",
        "name": "pydantic-ai-slim",
        "resource": "pydantic-ai-slim",
        "strategy": "registry",
        "subject_version": "2.51.0"
      }
    ]
  },
  "details": "### Summary\n\nThe Pydantic AI development web chat UI (`Agent.to_web()`, `clai web`) did not check the content type of requests to its chat endpoint. This allowed a website visited by a developer to submit a request to a chat UI running on that developer\u0027s machine, causing the served agent to run and to execute its tools with the privileges and credentials of the local process.\n\nBinding the web UI to localhost \u2014 the default \u2014 does not prevent this, because a page open in the developer\u0027s browser can reach the loopback address.\n\n### Impact\n\nApplications and developers serving an agent through `Agent.to_web()` or `clai web`. The consequences depend on the tools the served agent exposes, and can include data disclosure as well as unwanted tool side effects. Tools marked `requires_approval=True` were not protected either, because the endpoint trusts approval decisions relayed by the client.\n\n### Mitigation\n\nUpgrade to a patched version. The chat endpoint now requires `Content-Type: application/json` and rejects other requests before the request body is parsed and before the agent runs. The bundled chat UI already sends this header; scripts and other non-browser clients that call the endpoint directly may need to be updated to send it.\n\nIf you cannot upgrade, don\u0027t run the web UI while browsing untrusted sites, stop it when you aren\u0027t using it, and don\u0027t serve an agent with side-effecting tools through it.\n\n### Credits\n- Thai Son Dinh from VinSOC Labs (R\u0026D)",
  "id": "BREW-oterm-CVE-2026-107295",
  "modified": "2026-10-08T18:40:35Z",
  "published": "2026-10-08T18:40:35Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-h4xc-3qfq-jf93"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/pull/7382"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/pull/7383"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/commit/d2690201a1834005d382dbf5c47e0ed94ef8bf46"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/commit/dd2abbdfa029c9ad138e7cc0edd2eaeaf9ed69c0"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/pydantic/pydantic-ai"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.4"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/releases/tag/v2.28.0"
    }
  ],
  "schema_version": "1.7.3",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): a website visited by the developer can trigger agent runs and server-side tool execution on the local chat endpoint",
  "upstream": [
    "GHSA-h4xc-3qfq-jf93",
    "CVE-2026-107295"
  ]
}

FKIE_CVE-2026-107295

Vulnerability from fkie_nvd - Published: 2026-10-08 17:17 - Updated: 2026-10-08 20:35

Severity

7.6 (High) - CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L

Summary

References

	URL	Tags
	security-advisories@github.com	https://github.com/pydantic/pydantic-ai/commit/d2690201a1834005d382dbf5c47e0ed94ef8bf46
	security-advisories@github.com	https://github.com/pydantic/pydantic-ai/commit/dd2abbdfa029c9ad138e7cc0edd2eaeaf9ed69c0
	security-advisories@github.com	https://github.com/pydantic/pydantic-ai/pull/7382
	security-advisories@github.com	https://github.com/pydantic/pydantic-ai/pull/7383
	security-advisories@github.com	https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.4
	security-advisories@github.com	https://github.com/pydantic/pydantic-ai/releases/tag/v2.28.0
	security-advisories@github.com	https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-h4xc-3qfq-jf93

Impacted products

	Vendor	Product	Version

JSON

To clipboard

{
  "affected": [
    {
      "affectedData": [
        {
          "product": "pydantic-ai",
          "vendor": "pydantic",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 1.34.0, \u003c 1.107.4"
            },
            {
              "status": "affected",
              "version": "\u003e= 2.0.0b1, \u003c 2.28.0"
            }
          ]
        },
        {
          "product": "pydantic-ai-slim",
          "vendor": "pydantic",
          "versions": [
            {
              "status": "affected",
              "version": "\u003e= 1.34.0, \u003c 1.107.4"
            },
            {
              "status": "affected",
              "version": "\u003e= 2.0.0b1, \u003c 2.28.0"
            }
          ]
        }
      ],
      "source": "security-advisories@github.com"
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.34.0 until 1.107.4 and 2.28.0, the Agent.to_web() and clai web development chat endpoint has missing request content-type validation. A website visited by a developer can submit a browser-compatible request to a loopback-hosted chat server, causing the served agent to run and execute tools with the privileges and credentials of the local process; client-relayed approval decisions also leave requires_approval=True tools exposed. Binding to localhost does not prevent a browser page from reaching the loopback address. This issue is fixed in versions 1.107.4 and 2.28.0."
    }
  ],
  "id": "CVE-2026-107295",
  "lastModified": "2026-10-08T20:35:31.200",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "LOW",
          "baseScore": 7.6,
          "baseSeverity": "HIGH",
          "confidentialityImpact": "LOW",
          "integrityImpact": "HIGH",
          "privilegesRequired": "NONE",
          "scope": "UNCHANGED",
          "userInteraction": "REQUIRED",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L",
          "version": "3.1"
        },
        "exploitabilityScore": 2.8,
        "impactScore": 4.7,
        "source": "security-advisories@github.com",
        "type": "Secondary"
      }
    ],
    "ssvcV203": [
      {
        "source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
        "ssvcData": {
          "id": "CVE-2026-107295",
          "options": [
            {
              "exploitation": "none"
            },
            {
              "automatable": "no"
            },
            {
              "technicalImpact": "partial"
            }
          ],
          "role": "CISA Coordinator",
          "timestamp": "2026-10-08T17:53:16.989703Z",
          "version": "2.0.3"
        }
      }
    ]
  },
  "published": "2026-10-08T17:17:15.237",
  "references": [
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/pydantic/pydantic-ai/commit/d2690201a1834005d382dbf5c47e0ed94ef8bf46"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/pydantic/pydantic-ai/commit/dd2abbdfa029c9ad138e7cc0edd2eaeaf9ed69c0"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/pydantic/pydantic-ai/pull/7382"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/pydantic/pydantic-ai/pull/7383"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.4"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/pydantic/pydantic-ai/releases/tag/v2.28.0"
    },
    {
      "source": "security-advisories@github.com",
      "url": "https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-h4xc-3qfq-jf93"
    }
  ],
  "sourceIdentifier": "security-advisories@github.com",
  "vulnStatus": "Awaiting Analysis",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-352"
        }
      ],
      "source": "security-advisories@github.com",
      "type": "Secondary"
    }
  ]
}

GHSA-H4XC-3QFQ-JF93

Vulnerability from github – Published: 2026-10-08 17:16 – Updated: 2026-10-08 17:16

Summary

Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): a website visited by the developer can trigger agent runs and server-side tool execution on the local chat endpoint

Details

Summary

Binding the web UI to localhost — the default — does not prevent this, because a page open in the developer's browser can reach the loopback address.

Impact

Mitigation

If you cannot upgrade, don't run the web UI while browsing untrusted sites, stop it when you aren't using it, and don't serve an agent with side-effecting tools through it.

Credits

Thai Son Dinh from VinSOC Labs (R&D)

Severity

7.6 (High)


                  
                    CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "pydantic-ai"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "1.34.0"
            },
            {
              "fixed": "1.107.4"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "pydantic-ai"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "2.0.0b1"
            },
            {
              "fixed": "2.28.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "pydantic-ai-slim"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "1.34.0"
            },
            {
              "fixed": "1.107.4"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "pydantic-ai-slim"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "2.0.0b1"
            },
            {
              "fixed": "2.28.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-107295"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-346",
      "CWE-352"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-10-08T17:16:36Z",
    "nvd_published_at": null,
    "severity": "HIGH"
  },
  "details": "### Summary\n\nThe Pydantic AI development web chat UI (`Agent.to_web()`, `clai web`) did not check the content type of requests to its chat endpoint. This allowed a website visited by a developer to submit a request to a chat UI running on that developer\u0027s machine, causing the served agent to run and to execute its tools with the privileges and credentials of the local process.\n\nBinding the web UI to localhost \u2014 the default \u2014 does not prevent this, because a page open in the developer\u0027s browser can reach the loopback address.\n\n### Impact\n\nApplications and developers serving an agent through `Agent.to_web()` or `clai web`. The consequences depend on the tools the served agent exposes, and can include data disclosure as well as unwanted tool side effects. Tools marked `requires_approval=True` were not protected either, because the endpoint trusts approval decisions relayed by the client.\n\n### Mitigation\n\nUpgrade to a patched version. The chat endpoint now requires `Content-Type: application/json` and rejects other requests before the request body is parsed and before the agent runs. The bundled chat UI already sends this header; scripts and other non-browser clients that call the endpoint directly may need to be updated to send it.\n\nIf you cannot upgrade, don\u0027t run the web UI while browsing untrusted sites, stop it when you aren\u0027t using it, and don\u0027t serve an agent with side-effecting tools through it.\n\n### Credits\n- Thai Son Dinh from VinSOC Labs (R\u0026D)",
  "id": "GHSA-h4xc-3qfq-jf93",
  "modified": "2026-10-08T17:16:36Z",
  "published": "2026-10-08T17:16:36Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-h4xc-3qfq-jf93"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/pull/7382"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/pull/7383"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/commit/d2690201a1834005d382dbf5c47e0ed94ef8bf46"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/commit/dd2abbdfa029c9ad138e7cc0edd2eaeaf9ed69c0"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/pydantic/pydantic-ai"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.4"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/releases/tag/v2.28.0"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Pydantic AI Web chat UI (`Agent.to_web()`, `clai web`): a website visited by the developer can trigger agent runs and server-side tool execution on the local chat endpoint"
}

Sightings

Author	Source	Type	Date	Other

Nomenclature

Seen: The vulnerability was mentioned, discussed, or observed by the user.
Confirmed: The vulnerability has been validated from an analyst's perspective.
Published Proof of Concept: A public proof of concept is available for this vulnerability.
Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
Not confirmed: The user expressed doubt about the validity of the vulnerability.
Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.

The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base model, served locally by ML-Gateway. They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.

Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.

Action not permitted

CVE-2026-107295 (GCVE-0-2026-107295)

BREW-OTERM-CVE-2026-107295 (GHSA-H4XC-3QFQ-JF93)

Summary

Impact

Mitigation

Credits

FKIE_CVE-2026-107295

GHSA-H4XC-3QFQ-JF93

Summary

Impact

Mitigation

Credits

Tags

Sightings

Nomenclature

Related by attack behaviour