pydantic-ai
Affected
- introduced
1.77.0, fixed1.107.7(ecosystem)
Fixed versions
1.107.7
Fix
- Fixed version
1.107.7pip install --upgrade pydantic-ai==1.107.7
Advisory
Also known as: CVE-2026-107287, PYSEC-2026-4281, PYSEC-2026-4290
Pydantic AI: Excessive resource use when local web fetching converts nested HTML
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.
Medium Basis: The source's own band: MODERATE
1.77.0, fixed 1.107.7 (ecosystem)1.107.7
1.107.7pip install --upgrade pydantic-ai==1.107.72.0.0b1, fixed 2.52.0 (ecosystem)2.52.0
2.52.0pip install --upgrade pydantic-ai==2.52.01.77.0, fixed 1.107.7 (ecosystem)1.107.7
1.107.7pip install --upgrade pydantic-ai-slim==1.107.72.0.0b1, fixed 2.52.0 (ecosystem)2.52.0
2.52.0pip install --upgrade pydantic-ai-slim==2.52.0Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.
Check your own computer: guard packages check
Source: GitHub Advisory Database (reviewed advisories) · CC BY 4.0