GHSA-H4XC-3QFQ-JF93

Vulnerability from github – Published: 2026-10-08 17:16 – Updated: 2026-10-08 17:16
VLAI
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
Show details on source website
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"
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.

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.



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.