Skip to content
Fencer Intel
medium 6.5

CVE-2026-107287 json

Pydantic AI: Excessive resource use when local web fetching converts nested HTML

published last mo. modified 25d ago also EUVD-2026-95075 , GHSA-v36g-jcw9-x7cw , PYSEC-2026-4281 , PYSEC-2026-4290

cvss
6.5
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.3%
EPSS 0.3% chance of exploitation in 30 days, percentile 20%
public exploits
0
none known

Summary

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.

Patch / fix

  • pypi pydantic-ai 1.107.7, 2.52.0
  • pypi pydantic-ai-slim 1.107.7, 2.52.0
  • pydantic pydantic_ai 1.107.7, 2.52.0
  • pydantic pydantic_ai_slim 1.107.7, 2.52.0

Is CVE-2026-107287 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.

Check with Fencer

Vendor advisories

What the vendors themselves say about their products: affected, fixed or not affected, and what to do.

red hat product security vex CVE-2026-107287 updated cvss 6.5

pydantic-ai: pydantic-ai: Denial of Service via resource exhaustion during HTML conversion

  • Red Hat Lightspeed Core lightspeed-core/lightspeed-stack-rhel9 Red Hat Enterprise Linux AI (RHEL AI) 3 rhelai3/bootc-cuda-rhel9, rhelai3/bootc-rocm-rhel9, rhelai3/bootc-gaudi-rhel9, rhelai3/disk-image-cuda-rhel9
    affected: workaround, no fix available “Fix deferred”

Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf

CISA SSVC

Exploitation
none
Automatable
no
Technical impact
partial
Assessed
27d ago

Exploit prediction

0.28% chance of exploitation in the next 30 days, higher than 20% of all scored CVEs (FIRST EPSS, 2026-11-09).

CVSS scores

assigned by version score vector
CNA 3.1 6.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H
GitHub 3.1 6.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H
OSV 3.1 6.5 CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H

Affected packages

ecosystem package affected fixed in
pypi pydantic-ai
>=1.77.0, <1.107.7
>=2.0.0b1, <2.52.0
1.107.7
2.52.0
pypi pydantic-ai-slim
>=1.77.0, <1.107.7
>=2.0.0b1, <2.52.0
1.107.7
2.52.0

Affected products

  • pydantic pydantic-ai
  • pydantic pydantic-ai-slim

Classification

Weakness
  • CWE-400 Uncontrolled Resource Consumption
  • CWE-407 Inefficient Algorithmic Complexity

References

Sources

Fencer Intel keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.