Vulnerability-Lookup

CVE-2026-82447 (GCVE-0-2026-82447)

Vulnerability from cvelistv5 – Published: 2026-08-29 12:05 – Updated: 2026-08-29 12:05

Title

Skyvern before 1.0.45 Sandbox Escape via TextPromptBlock

Summary

Skyvern before 1.0.45 contains a sandbox escape vulnerability in TextPromptBlock that renders prompts twice, first through a sandboxed Jinja environment and then through an unsandboxed environment. Attackers can inject malicious Jinja template syntax through workflow parameters or upstream block output to execute arbitrary code with server process privileges.

Severity

8.7 (High)


                        
                          CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

8.8 (High)


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

CWE

CWE-1336 - Improper Neutralization of Special Elements Used in a Template Engine

Assigner

VulnCheck mitre root

References

5 references

URL	Tags
https://github.com/Skyvern-AI/skyvern/commit/d723…	patch
https://github.com/Skyvern-AI/skyvern	product
https://github.com/Skyvern-AI/skyvern/blob/v1.0.4…	technical-description
https://github.com/Skyvern-AI/skyvern/blob/v1.0.4…	technical-description
https://www.vulncheck.com/advisories/skyvern-befo…	third-party-advisory

Impacted products

1 product

Vendor	Product	Version	CPE status
Skyvern-AI	skyvern	Affected: 0.2.1 , < 1.0.45 (semver)	guessed

Date Public

2026-07-06 00:00

Credits

hayato1121

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "cna": {
      "affected": [
        {
          "defaultStatus": "unaffected",
          "packageURL": "pkg:pypi/skyvern",
          "product": "skyvern",
          "vendor": "Skyvern-AI",
          "versions": [
            {
              "lessThan": "1.0.45",
              "status": "affected",
              "version": "0.2.1",
              "versionType": "semver"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "reporter",
          "value": "hayato1121"
        }
      ],
      "datePublic": "2026-07-06T00:00:00.000Z",
      "descriptions": [
        {
          "lang": "en",
          "value": "Skyvern before 1.0.45 contains a sandbox escape vulnerability in TextPromptBlock that renders prompts twice, first through a sandboxed Jinja environment and then through an unsandboxed environment. Attackers can inject malicious Jinja template syntax through workflow parameters or upstream block output to execute arbitrary code with server process privileges."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "baseScore": 8.7,
            "baseSeverity": "HIGH",
            "privilegesRequired": "LOW",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "HIGH",
            "vulnConfidentialityImpact": "HIGH",
            "vulnIntegrityImpact": "HIGH"
          },
          "format": "CVSS"
        },
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "HIGH",
            "baseScore": 8.8,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "LOW",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
            "version": "3.1"
          },
          "format": "CVSS"
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-1336",
              "description": "Improper Neutralization of Special Elements Used in a Template Engine",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-08-29T12:05:34.113Z",
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck"
      },
      "references": [
        {
          "name": "Patch Commit",
          "tags": [
            "patch"
          ],
          "url": "https://github.com/Skyvern-AI/skyvern/commit/d723de621d5b3a340f3cc4d5b46bfe40a9a3124e"
        },
        {
          "tags": [
            "product"
          ],
          "url": "https://github.com/Skyvern-AI/skyvern"
        },
        {
          "name": "Vulnerable code: block.py (sandboxed first render, non-sandboxed second render)",
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/workflow/models/block.py"
        },
        {
          "name": "Vulnerable code: prompting.py (PromptEngine uses a plain jinja2.Environment)",
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/prompting.py"
        },
        {
          "name": "VulnCheck Advisory: Skyvern before 1.0.45 Sandbox Escape via TextPromptBlock",
          "tags": [
            "third-party-advisory"
          ],
          "url": "https://www.vulncheck.com/advisories/skyvern-before-1.0.45-sandbox-escape-via-textpromptblock"
        }
      ],
      "title": "Skyvern before 1.0.45 Sandbox Escape via TextPromptBlock",
      "x_generator": {
        "engine": "vulncheck-endgame"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "cveId": "CVE-2026-82447",
    "datePublished": "2026-08-29T12:05:34.113Z",
    "dateReserved": "2026-08-29T11:37:29.518Z",
    "dateUpdated": "2026-08-29T12:05:34.113Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-82447\",\"sourceIdentifier\":\"disclosure@vulncheck.com\",\"published\":\"2026-08-29T13:16:38.643\",\"lastModified\":\"2026-08-29T13:16:38.643\",\"vulnStatus\":\"Received\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"Skyvern before 1.0.45 contains a sandbox escape vulnerability in TextPromptBlock that renders prompts twice, first through a sandboxed Jinja environment and then through an unsandboxed environment. Attackers can inject malicious Jinja template syntax through workflow parameters or upstream block output to execute arbitrary code with server process privileges.\"}],\"affected\":[{\"source\":\"disclosure@vulncheck.com\",\"affectedData\":[{\"vendor\":\"Skyvern-AI\",\"product\":\"skyvern\",\"defaultStatus\":\"unaffected\",\"packageURL\":\"pkg:pypi/skyvern\",\"versions\":[{\"version\":\"0.2.1\",\"lessThan\":\"1.0.45\",\"versionType\":\"semver\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV40\":[{\"source\":\"disclosure@vulncheck.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"4.0\",\"vectorString\":\"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X\",\"baseScore\":8.7,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"attackRequirements\":\"NONE\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"vulnConfidentialityImpact\":\"HIGH\",\"vulnIntegrityImpact\":\"HIGH\",\"vulnAvailabilityImpact\":\"HIGH\",\"subConfidentialityImpact\":\"NONE\",\"subIntegrityImpact\":\"NONE\",\"subAvailabilityImpact\":\"NONE\",\"exploitMaturity\":\"NOT_DEFINED\",\"confidentialityRequirement\":\"NOT_DEFINED\",\"integrityRequirement\":\"NOT_DEFINED\",\"availabilityRequirement\":\"NOT_DEFINED\",\"modifiedAttackVector\":\"NOT_DEFINED\",\"modifiedAttackComplexity\":\"NOT_DEFINED\",\"modifiedAttackRequirements\":\"NOT_DEFINED\",\"modifiedPrivilegesRequired\":\"NOT_DEFINED\",\"modifiedUserInteraction\":\"NOT_DEFINED\",\"modifiedVulnConfidentialityImpact\":\"NOT_DEFINED\",\"modifiedVulnIntegrityImpact\":\"NOT_DEFINED\",\"modifiedVulnAvailabilityImpact\":\"NOT_DEFINED\",\"modifiedSubConfidentialityImpact\":\"NOT_DEFINED\",\"modifiedSubIntegrityImpact\":\"NOT_DEFINED\",\"modifiedSubAvailabilityImpact\":\"NOT_DEFINED\",\"Safety\":\"NOT_DEFINED\",\"Automatable\":\"NOT_DEFINED\",\"Recovery\":\"NOT_DEFINED\",\"valueDensity\":\"NOT_DEFINED\",\"vulnerabilityResponseEffort\":\"NOT_DEFINED\",\"providerUrgency\":\"NOT_DEFINED\"}}],\"cvssMetricV31\":[{\"source\":\"disclosure@vulncheck.com\",\"type\":\"Primary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H\",\"baseScore\":8.8,\"baseSeverity\":\"HIGH\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"HIGH\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":2.8,\"impactScore\":5.9}]},\"weaknesses\":[{\"source\":\"disclosure@vulncheck.com\",\"type\":\"Primary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-1336\"}]}],\"references\":[{\"url\":\"https://github.com/Skyvern-AI/skyvern\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/prompting.py\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/workflow/models/block.py\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://github.com/Skyvern-AI/skyvern/commit/d723de621d5b3a340f3cc4d5b46bfe40a9a3124e\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://www.vulncheck.com/advisories/skyvern-before-1.0.45-sandbox-escape-via-textpromptblock\",\"source\":\"disclosure@vulncheck.com\"}]}}"
  }
}

FKIE_CVE-2026-82447

Vulnerability from fkie_nvd - Published: 2026-08-29 13:16 - Updated: 2026-08-29 13:16

Severity

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

Summary

References

	URL	Tags
	disclosure@vulncheck.com	https://github.com/Skyvern-AI/skyvern
	disclosure@vulncheck.com	https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/prompting.py
	disclosure@vulncheck.com	https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/workflow/models/block.py
	disclosure@vulncheck.com	https://github.com/Skyvern-AI/skyvern/commit/d723de621d5b3a340f3cc4d5b46bfe40a9a3124e
	disclosure@vulncheck.com	https://www.vulncheck.com/advisories/skyvern-before-1.0.45-sandbox-escape-via-textpromptblock

Impacted products

	Vendor	Product	Version

JSON

To clipboard

{
  "affected": [
    {
      "affectedData": [
        {
          "defaultStatus": "unaffected",
          "packageURL": "pkg:pypi/skyvern",
          "product": "skyvern",
          "vendor": "Skyvern-AI",
          "versions": [
            {
              "lessThan": "1.0.45",
              "status": "affected",
              "version": "0.2.1",
              "versionType": "semver"
            }
          ]
        }
      ],
      "source": "disclosure@vulncheck.com"
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "Skyvern before 1.0.45 contains a sandbox escape vulnerability in TextPromptBlock that renders prompts twice, first through a sandboxed Jinja environment and then through an unsandboxed environment. Attackers can inject malicious Jinja template syntax through workflow parameters or upstream block output to execute arbitrary code with server process privileges."
    }
  ],
  "id": "CVE-2026-82447",
  "lastModified": "2026-08-29T13:16:38.643",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "LOW",
          "attackVector": "NETWORK",
          "availabilityImpact": "HIGH",
          "baseScore": 8.8,
          "baseSeverity": "HIGH",
          "confidentialityImpact": "HIGH",
          "integrityImpact": "HIGH",
          "privilegesRequired": "LOW",
          "scope": "UNCHANGED",
          "userInteraction": "NONE",
          "vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
          "version": "3.1"
        },
        "exploitabilityScore": 2.8,
        "impactScore": 5.9,
        "source": "disclosure@vulncheck.com",
        "type": "Primary"
      }
    ],
    "cvssMetricV40": [
      {
        "cvssData": {
          "Automatable": "NOT_DEFINED",
          "Recovery": "NOT_DEFINED",
          "Safety": "NOT_DEFINED",
          "attackComplexity": "LOW",
          "attackRequirements": "NONE",
          "attackVector": "NETWORK",
          "availabilityRequirement": "NOT_DEFINED",
          "baseScore": 8.7,
          "baseSeverity": "HIGH",
          "confidentialityRequirement": "NOT_DEFINED",
          "exploitMaturity": "NOT_DEFINED",
          "integrityRequirement": "NOT_DEFINED",
          "modifiedAttackComplexity": "NOT_DEFINED",
          "modifiedAttackRequirements": "NOT_DEFINED",
          "modifiedAttackVector": "NOT_DEFINED",
          "modifiedPrivilegesRequired": "NOT_DEFINED",
          "modifiedSubAvailabilityImpact": "NOT_DEFINED",
          "modifiedSubConfidentialityImpact": "NOT_DEFINED",
          "modifiedSubIntegrityImpact": "NOT_DEFINED",
          "modifiedUserInteraction": "NOT_DEFINED",
          "modifiedVulnAvailabilityImpact": "NOT_DEFINED",
          "modifiedVulnConfidentialityImpact": "NOT_DEFINED",
          "modifiedVulnIntegrityImpact": "NOT_DEFINED",
          "privilegesRequired": "LOW",
          "providerUrgency": "NOT_DEFINED",
          "subAvailabilityImpact": "NONE",
          "subConfidentialityImpact": "NONE",
          "subIntegrityImpact": "NONE",
          "userInteraction": "NONE",
          "valueDensity": "NOT_DEFINED",
          "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
          "version": "4.0",
          "vulnAvailabilityImpact": "HIGH",
          "vulnConfidentialityImpact": "HIGH",
          "vulnIntegrityImpact": "HIGH",
          "vulnerabilityResponseEffort": "NOT_DEFINED"
        },
        "source": "disclosure@vulncheck.com",
        "type": "Secondary"
      }
    ]
  },
  "published": "2026-08-29T13:16:38.643",
  "references": [
    {
      "source": "disclosure@vulncheck.com",
      "url": "https://github.com/Skyvern-AI/skyvern"
    },
    {
      "source": "disclosure@vulncheck.com",
      "url": "https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/prompting.py"
    },
    {
      "source": "disclosure@vulncheck.com",
      "url": "https://github.com/Skyvern-AI/skyvern/blob/v1.0.44/skyvern/forge/sdk/workflow/models/block.py"
    },
    {
      "source": "disclosure@vulncheck.com",
      "url": "https://github.com/Skyvern-AI/skyvern/commit/d723de621d5b3a340f3cc4d5b46bfe40a9a3124e"
    },
    {
      "source": "disclosure@vulncheck.com",
      "url": "https://www.vulncheck.com/advisories/skyvern-before-1.0.45-sandbox-escape-via-textpromptblock"
    }
  ],
  "sourceIdentifier": "disclosure@vulncheck.com",
  "vulnStatus": "Received",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-1336"
        }
      ],
      "source": "disclosure@vulncheck.com",
      "type": "Primary"
    }
  ]
}

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.

Detection rules are retrieved from Rulezet.

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.

Action not permitted

CVE-2026-82447 (GCVE-0-2026-82447)

FKIE_CVE-2026-82447

Tags

Sightings

Nomenclature