Browse / Unbounded Consumption / CVE-2026-107294
Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl
- Class
- Unbounded Consumption (filed by a model that read the advisory)
- Technique
- Denial of service
- Affected
- pydantic-ai (PyPI)
- CVSS
- CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H
- EPSS
- 0.4% chance of exploitation in 30 days
How it works, in short
An agent's web-fetch tool buffers the entire response from a model-chosen URL before size limits apply, so a large body exhausts worker memory. (Our summary, written by a model. The source text is below.)
Details
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 FileUrls 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.
References
- https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-v2xh-2vp8-57h8
- https://github.com/pydantic/pydantic-ai/pull/7141
- https://github.com/pydantic/pydantic-ai/pull/7308
- https://github.com/pydantic/pydantic-ai/commit/7a64d049c3f5271a975cd1d64b2fa876d83ede1d
- https://github.com/pydantic/pydantic-ai/commit/e3824a58c82864ed26afb2887619834a4eb86cc8
- https://github.com/pydantic/pydantic-ai
- https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.2
- https://github.com/pydantic/pydantic-ai/releases/tag/v2.24.0
Source: GitHub Advisory Database, used under CC BY 4.0.