GHSA-V36G-JCW9-X7CW

Vulnerability from github – Published: 2026-10-08 17:40 – Updated: 2026-10-08 17:40
VLAI
Summary
Pydantic AI: Excessive resource use when local web fetching converts nested HTML
Details

Summary

Applications using Pydantic AI's local web-fetch tool can experience excessive CPU and memory use when it converts attacker-controlled HTML. An agent must fetch the affected page; provider-native web fetching is not affected.

Details

Nested block elements cause HTML-to-Markdown conversion to reprocess accumulated text at each level and can greatly expand the intermediate output. The response-body limit bounds downloaded bytes, while the returned-content limit is applied only after conversion. On current releases, conversion runs in a worker thread but can still consume substantial resources and delay other work in the process. Older releases performed conversion on the event loop.

Mitigation

Upgrade to a patched release of pydantic-ai or pydantic-ai-slim. If you cannot upgrade yet, avoid using local web fetching for attacker-controlled HTML.

Severity
6.5 (Medium)
CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "pydantic-ai"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "1.77.0"
            },
            {
              "fixed": "1.107.7"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "pydantic-ai"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "2.0.0b1"
            },
            {
              "fixed": "2.52.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "pydantic-ai-slim"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "1.77.0"
            },
            {
              "fixed": "1.107.7"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "pydantic-ai-slim"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "2.0.0b1"
            },
            {
              "fixed": "2.52.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-107287"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-400",
      "CWE-407"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-10-08T17:40:50Z",
    "nvd_published_at": null,
    "severity": "MODERATE"
  },
  "details": "### Summary\n\nApplications using Pydantic AI\u0027s local web-fetch tool can experience excessive CPU and memory use when it converts attacker-controlled HTML. An agent must fetch the affected page; provider-native web fetching is not affected.\n\n### Details\n\nNested block elements cause HTML-to-Markdown conversion to reprocess accumulated text at each level and can greatly expand the intermediate output. The response-body limit bounds downloaded bytes, while the returned-content limit is applied only after conversion. On current releases, conversion runs in a worker thread but can still consume substantial resources and delay other work in the process. Older releases performed conversion on the event loop.\n\n### Mitigation\n\nUpgrade to a patched release of `pydantic-ai` or `pydantic-ai-slim`. If you cannot upgrade yet, avoid using local web fetching for attacker-controlled HTML.",
  "id": "GHSA-v36g-jcw9-x7cw",
  "modified": "2026-10-08T17:40:50Z",
  "published": "2026-10-08T17:40:50Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-v36g-jcw9-x7cw"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/pull/8984"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/pull/8985"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/commit/2b247add4950bef61d352e7ca8aefbd20539180c"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/commit/2fd38792693da00a3ca5412aeffb436787af3545"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/pydantic/pydantic-ai"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.7"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pydantic/pydantic-ai/releases/tag/v2.52.0"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Pydantic AI: Excessive resource use when local web fetching converts nested HTML"
}



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.