Answer in brief
CVE-2026-107295 records a High severity (CVSS 7.6) vulnerability in `pydantic-ai-slim` web UI `/api/chat` accepts browser-simple cross-origin requests that can trigger agent tool execution. The current sources do not mark it as known exploited. The current feed maps pydantic/pydantic-ai (generic), pydantic/pydantic-ai-slim (generic), pydantic-ai (pip), pydantic-ai (pip) and additional mapped packages. Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 7.6. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps pydantic/pydantic-ai (generic), pydantic/pydantic-ai-slim (generic), pydantic-ai (pip), pydantic-ai (pip) and additional mapped packages. Check affected ranges and fixed versions before updating.
| Package | Affected range | Fixed version |
|---|---|---|
| pydantic/pydantic-aigeneric | >=1.34.0 <1.107.4 || >=2.0.0b1 <2.28.0 | 1.107.4, 2.28.0 |
| pydantic/pydantic-ai-slimgeneric | >=1.34.0 <1.107.4 || >=2.0.0b1 <2.28.0 | 1.107.4, 2.28.0 |
| pydantic-aipip | >=1.34.0,<1.107.4 | 1.107.4 |
| pydantic-aipip | >=2.0.0b1,<2.28.0 | 2.28.0 |
| pydantic-ai-slimpip | >=1.34.0,<1.107.4 | 1.107.4 |
| pydantic-ai-slimpip | >=2.0.0b1,<2.28.0 | 2.28.0 |
Published upstream
Oct 8, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Oct 8, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Oct 8, 2026
Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.34.0 until 1.107.4 and 2.28.0, the Agent.to_web() and clai web development chat endpoint has missing request content-type validation. A website visited by a developer can submit a browser-compatible request to a loopback-hosted chat server, causing the served agent to run and execute tools with the privileges and credentials of the local process; client-relayed approval decisions also leave requires_approval=True tools exposed. Binding to localhost does not prevent a browser page from reaching the loopback address. This issue is fixed in versions 1.107.4 and 2.28.0.
Quoted source text, attributed separately from HOL analysis.