GitHub Advisoryadvisory · PyPI
GHSA-v2xh-2vp8-57h8 Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl
MEDIUM
Official page ↗
- Aliases
- CVE-2026-107294
- Ecosystem
- PyPI
- Packages
- pydantic-ai, pydantic-ai-slim
- Severity
- Moderate
- CVSS vector
- CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- Weaknesses
- CWE-400, CWE-770
- Reviewed
- 2026-10-08
Affected packages
• PyPI pydantic-ai: >= 1.77.0, < 1.107.2 → fixed in 1.107.2
• PyPI pydantic-ai: >= 2.0.0b1, < 2.24.0 → fixed in 2.24.0
• PyPI pydantic-ai-slim: >= 1.77.0, < 1.107.2 → fixed in 1.107.2
• PyPI pydantic-ai-slim: >= 2.0.0b1, < 2.24.0 → fixed in 2.24.0
Description
Summary
Several remote-content download paths in Pydantic AI buffered the entire HTTP response body into memory before enforcing any size limit. An application that exposes the local web-fetch tool (`web_fetch_tool`, or the `WebFetch` capability's local fallback) to untrusted prompts can be driven to fetch an attacker-chosen URL that streams a very large body, exhausting process memory and crashing the worker. The same unbounded buffering applied to `FileUrl` media downloads (`ImageUrl`, `DocumentUrl`, `VideoUrl`, `AudioUrl`).
This is an availability issue only. SSRF protections (scheme allowlist, private-IP and cloud-metadata blocking) are unaffected; there is no confidentiality or integrity impact.
Details
The download helpers read the full response body before applying content-size controls, so an existing text-length limit only truncated *after* the whole body was already in memory, and media downloads had no wire-level cap at all. A single large response could grow process memory without bound .
Who Is Affected
You are affected if your application registers the local web-fetch tool (or relies on the `WebFetch` capability's local fallback) and exposes the agent to untrusted prompts, or if it downloads large remote `FileUrl`s influenced by untrusted input. Applications that only fetch developer-controlled URLs are not exposed to the model-chosen attack path.
Remediation
Upgrade to `2.24.0` or later (v2) or `1.107.2` or later (v1). Patched versions enforce a default 50 MiB cap on web-fetch and `FileUrl` downloads while streaming; pass `None` to the limit to restore the previous unbounded behavior.
Credits
Identified during internal review of media-download hardening.
Related
Alias · CVE (1)
- CVE-2026-107294 Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. vulnerability
References
- https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-v2xh-2vp8-57h8 web
- https://github.com/pydantic/pydantic-ai/pull/7141 web
- https://github.com/pydantic/pydantic-ai/pull/7308 web
- https://github.com/pydantic/pydantic-ai/commit/7a64d049c3f5271a975cd1d64b2fa876d83ede1d web
- https://github.com/pydantic/pydantic-ai/commit/e3824a58c82864ed26afb2887619834a4eb86cc8 web
- https://github.com/pydantic/pydantic-ai package
- https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.2 web
- https://github.com/pydantic/pydantic-ai/releases/tag/v2.24.0 web