Summary
Pydantic AI: Unbounded memory use when downloading remote content via web_fetch or FileUrl
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.
Credits
Identified during internal review of media-download hardening.
Impact
Crafted input forces the application to consume excessive CPU, memory, or other resources, degrading or denying service. Typical impact: denial of service.
CVE-2026-107294 has a CVSS score of 6.5 (Medium). The vector is network-reachable, low privileges required, and no user interaction. A CVSS score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether this affects your application depends on whether the vulnerable code is present and reachable in your environment. A fixed version is available (1.107.2, 2.24.0); upgrading removes the vulnerable code path.
Affected versions
Security releases
Kodem intelligence
Severity tells you how bad this could be in the worst case. It does not tell you whether you are exposed. Exploitability and impact are functions of runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A vulnerable package can sit in your dependency tree and never run.
Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter. Kodem's runtime-powered SCA identifies whether this CVE is reachable in your applications.
Already deployed Kodem?
See it in your environmentNew to Kodem? Get a demo →Remediation advice
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.
Frequently Asked Questions
- What is CVE-2026-107294? CVE-2026-107294 is a medium-severity uncontrolled resource consumption vulnerability in pydantic-ai (pip), affecting versions >= 1.77.0, < 1.107.2. It is fixed in 1.107.2, 2.24.0. Crafted input forces the application to consume excessive CPU, memory, or other resources, degrading or denying service.
- How severe is CVE-2026-107294? CVE-2026-107294 has a CVSS score of 6.5 (Medium). This score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether it represents real risk in your environment depends on whether the vulnerable code is present and reachable.
- Which packages are affected by CVE-2026-107294?
pydantic-ai(pip) (versions >= 1.77.0, < 1.107.2)pydantic-ai-slim(pip) (versions >= 1.77.0, < 1.107.2)
- Is there a fix for CVE-2026-107294? Yes. CVE-2026-107294 is fixed in 1.107.2, 2.24.0. Upgrade to this version or later.
- Is CVE-2026-107294 exploitable, and should I be worried? Whether CVE-2026-107294 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
- What actually determines whether CVE-2026-107294 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
- How do I fix CVE-2026-107294?
- Upgrade
pydantic-aito 1.107.2 or later - Upgrade
pydantic-aito 2.24.0 or later - Upgrade
pydantic-ai-slimto 1.107.2 or later - Upgrade
pydantic-ai-slimto 2.24.0 or later
- Upgrade