What’s Vulnerable › Vulnerabilities

CVE-2026-107295: `pydantic-ai-slim` web UI `/api/chat` accepts browser-simple cross-origin requests that can trigger agent tool execution

• Severity: high (CVSS 7.6 v3.1)
• Exploited in the wild: not listed in CISA KEV
• EPSS: 0.2% probability of exploitation in the next 30 days
• Public exploit or detection template: none known
• Published: 2026-10-08 · updated 2026-10-13
• Weakness: CWE-352

Description

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.

Affected products

• pydantic-ai: from 1.34.0 before 1.107.4; from 2.0.0 before 2.28.0 — fixed in 1.107.4, 2.28.0

How to fix

Upgrade to a fixed version: pydantic-ai 1.107.4, 2.28.0. Check the vendor advisory for mitigations.

References

• https://github.com/pydantic/pydantic-ai/commit/d2690201a1834005d382dbf5c47e0ed94ef8bf46
• https://github.com/pydantic/pydantic-ai/commit/dd2abbdfa029c9ad138e7cc0edd2eaeaf9ed69c0
• https://github.com/pydantic/pydantic-ai/pull/7382
• https://github.com/pydantic/pydantic-ai/pull/7383
• https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.4
• https://github.com/pydantic/pydantic-ai/releases/tag/v2.28.0
• https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-h4xc-3qfq-jf93

Get alerted when CVE-2026-107295 or the next vulnerability affects your stack