CVE-2026-107287: Pydantic AI: Excessive resource use when local web fetching converts nested HTML
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.
References
- github.com/advisories/GHSA-v36g-jcw9-x7cw
- github.com/pydantic/pydantic-ai/commit/2b247add4950bef61d352e7ca8aefbd20539180c
- github.com/pydantic/pydantic-ai/commit/2fd38792693da00a3ca5412aeffb436787af3545
- github.com/pydantic/pydantic-ai/pull/8984
- github.com/pydantic/pydantic-ai/pull/8985
- github.com/pydantic/pydantic-ai/releases/tag/v1.107.7
- github.com/pydantic/pydantic-ai/releases/tag/v2.52.0
- github.com/pydantic/pydantic-ai/security/advisories/GHSA-v36g-jcw9-x7cw
- nvd.nist.gov/vuln/detail/CVE-2026-107287
Code Behaviors & Features
Detect and mitigate CVE-2026-107287 with GitLab Dependency Scanning
Secure your software supply chain by verifying that all open source dependencies used in your projects contain no disclosed vulnerabilities. Learn more about Dependency Scanning →