Excessive resource use in Pydantic AI HTML-to-Markdown web fetching
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- Required
- Attack complexity
- Low
- Impact type
- Denial of service
- Confidentiality · integrity · availability
- None · None · High
- Fix status
- Partial Red Hat: 2 without a fix
Attack profile from CVSS 3.1 · CNA. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-400.
Summary
The Pydantic AI packages pydantic-ai and pydantic-ai-slim from 1.77.0 before 1.107.7 and from 2.0.0b1 before 2.52.0 are affected. The local web_fetch_tool and WebFetch fallback repeatedly reprocess accumulated text during HTML-to-Markdown conversion, which is an inefficient algorithm (CWE-407). An attacker who controls fetched HTML with deeply nested block elements can use a model-directed fetch to consume excessive CPU and memory and delay other work in the process. Provider-native web fetching is not affected.
Written with Claude Haiku 5.5 from the sources below · 2026-10-29
Description from the CNA
Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. From 1.77.0 until 1.107.7 and 2.52.0, the local web_fetch_tool and the WebFetch local fallback can consume excessive CPU and memory during HTML-to-Markdown conversion of attacker-controlled HTML containing deeply nested block elements. Conversion repeatedly reprocesses accumulated text and can greatly expand intermediate output before the returned-content limit is applied, allowing a model-directed fetch to delay other work in the process. Provider-native web fetching is not affected. This issue is fixed in versions 1.107.7 and 2.52.0.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- None
- Automatable
- No
- Technical impact
- Partial
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| pydantic | pydantic-ai | 1.77.0 to before 1.107.7; 2.0.0b1 to before 2.52.0 | 1.107.7, 2.52.0 | Patch available | CNA |
| pydantic | pydantic-ai-slim | 1.77.0 to before 1.107.7; 2.0.0b1 to before 2.52.0 | 1.107.7, 2.52.0 | Patch available | CNA |
| — | pydantic-ai (PyPI) | 1.77.0 to before 1.107.7 | 1.107.7 | Patch available | GHSA-v36g-jcw9-x7cw |
| — | pydantic-ai (PyPI) | 2.0.0b1 to before 2.52.0 | 2.52.0 | Patch available | GHSA-v36g-jcw9-x7cw |
| — | pydantic-ai-slim (PyPI) | 1.77.0 to before 1.107.7 | 1.107.7 | Patch available | GHSA-v36g-jcw9-x7cw |
| — | pydantic-ai-slim (PyPI) | 2.0.0b1 to before 2.52.0 | 2.52.0 | Patch available | GHSA-v36g-jcw9-x7cw |
- pydantic-ai Vendorpydantic Affected 1.77.0 to before 1.107.7; 2.0.0b1 to before 2.52.0 Fixed in 1.107.7, 2.52.0 Patch available CNA
- pydantic-ai-slim Vendorpydantic Affected 1.77.0 to before 1.107.7; 2.0.0b1 to before 2.52.0 Fixed in 1.107.7, 2.52.0 Patch available CNA
- pydantic-ai (PyPI) Vendor— Affected 1.77.0 to before 1.107.7 Fixed in 1.107.7 Patch available GHSA-v36g-jcw9-x7cw
- pydantic-ai (PyPI) Vendor— Affected 2.0.0b1 to before 2.52.0 Fixed in 2.52.0 Patch available GHSA-v36g-jcw9-x7cw
- pydantic-ai-slim (PyPI) Vendor— Affected 1.77.0 to before 1.107.7 Fixed in 1.107.7 Patch available GHSA-v36g-jcw9-x7cw
- pydantic-ai-slim (PyPI) Vendor— Affected 2.0.0b1 to before 2.52.0 Fixed in 2.52.0 Patch available GHSA-v36g-jcw9-x7cw
Remediation
Upgrade pydantic-ai and pydantic-ai-slim to 1.107.7 on the 1.x line or to 2.52.0 on the 2.x line. Red Hat's plan for Lightspeed Core and Red Hat Enterprise Linux AI (RHEL AI) 3 is none available.
Written with Claude Haiku 5.5 from the sources below · 2026-10-29
- Fix · CNA pydantic-ai (pydantic) Fixed in 1.107.7, 2.52.0
- Fix · CNA pydantic-ai-slim (pydantic) Fixed in 1.107.7, 2.52.0
- Fix · GHSA-v36g-jcw9-x7cw pydantic-ai (PyPI) Fixed in 1.107.7 Advisory →
- Fix · GHSA-v36g-jcw9-x7cw pydantic-ai (PyPI) Fixed in 2.52.0 Advisory →
- Fix · GHSA-v36g-jcw9-x7cw pydantic-ai-slim (PyPI) Fixed in 1.107.7 Advisory →
- Fix · GHSA-v36g-jcw9-x7cw pydantic-ai-slim (PyPI) Fixed in 2.52.0 Advisory →
Vendor assessments
Red Hat
Red Hat rating: Moderate. Red Hat's page for this CVE →
| Product | Status | Plan or fix |
|---|---|---|
| Lightspeed Core | Affected | No fix yet: Fix deferred |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | Affected | No fix yet: Fix deferred |
Timeline
- 2026-10-08 Threatist record created from CVE-2026-107287
- 2026-10-08 Alias added: GHSA-v36g-jcw9-x7cw
- 2026-10-09 Affected versions changed · Red Hat
- 2026-10-09 CVSS score added · Red Hat
- 2026-10-10 Priority changed: MEDIUM → LOW
- 2026-10-14 CISA SSVC decision points changed
References
Patch 6
- https://github.com/pydantic/pydantic-ai/pull/8984
- https://github.com/pydantic/pydantic-ai/pull/8985
- https://github.com/pydantic/pydantic-ai/commit/2b247add4950bef61d352e7ca8aefbd20539180c
- https://github.com/pydantic/pydantic-ai/commit/2fd38792693da00a3ca5412aeffb436787af3545
- https://github.com/pydantic/pydantic-ai/releases/tag/v1.107.7
- https://github.com/pydantic/pydantic-ai/releases/tag/v2.52.0
More Pydantic Ai vulnerabilities
- TI-2026-20687 Pydantic AI Affected by Server-Side Request Forgery (SSRF) in URL Download Handling CVSS 3.1HIGH 8.6
- TI-2026-69551 Pydantic AI keeps concurrency slots after streams end early CVSS 3.1HIGH 7.5
- TI-2026-46990 Incorrect authorization in pydantic-ai CVSS 3.1MEDIUM 6.5
- TI-2026-69610 Cross-site requests run agent tools in pydantic-ai web chat CVSS 3.1HIGH 7.6
- TI-2026-20740 Pydantic AI affected by Stored XSS via Path Traversal in Web UI CDN URL CVSS 3.1HIGH 7.1
- TI-2026-69617 Pydantic AI blocklist bypass via IPv6 zone identifier allows SSRF CVSS 3.1MEDIUM 6.8
Sources
- CVE-2026-107287 · CVE Program
- CVE-2026-107287 · NVD
- FIRST EPSS
- GHSA-v36g-jcw9-x7cw · GitHub Advisory Database · CC BY 4.0
- CVE-2026-107287 · Red Hat security data · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences