AdvisoriesToolsStatsChecklistSubmitGet the email
← All tools
LLM frameworks · Pydantic

Pydantic AI

Python framework for building AI agents, from the Pydantic team.

1Advisories
0critical
1high
0medium
2026-10-08Latest
Pydantic AI CVEs & security

Is Pydantic AI safe?

Pydantic AI is the Pydantic team's Python framework for building AI agents.

We track 1 security advisory that affects Pydantic AI. By severity: 1 high. It has a CVE ID. It is a agent hijacking issue. The newest entry is dated 2026-10-08.

Newest entries on this page
Using Pydantic AI safely
  • Treat model output and tool arguments as untrusted input, and validate them before acting.
  • Give agents only the tools they need, and don't let tools run shell commands or arbitrary code without a sandbox.
  • If your agent reads web pages, emails or documents, assume they can contain prompt injection.
  • Keep the package and its model-provider SDKs updated, and pin versions in production.
Timeline · advisories per quarter
12026 Q4
Named in sources

Reported for Pydantic AI

01. highAgent hijackingCVE-2026-107295: any website can make the Pydantic AI web chat UI (Agent.to_web, clai web) run your agent and its tools, upgrade to 1.107.4 or 2.28.0Pydantic AI's development web chat UI (Agent.to_web() and clai web) didn't check the content type of requests to its chat endpoint. A website open in the developer's browser could send a request to the local UI and make the agent run its tools with the local process's privileges, even when bound to localhost. Tools marked requires_approval=True weren't protected either. Pydantic AI 2026-10-08
The weekly email

One email a week. Only what changed.

Every new security hole in AI coding tools, MCP servers, app builders and the stacks they generate (Next.js, Supabase, Node, PHP), each with how to check your app and the fix. No roundups of things you already read.

Free, one email a week. Read the latest issue first if you like. One-click unsubscribe in every email. We never sell or share addresses.