Vulnerability · Published Oct 21, 2026 · Assigned by VulnCheck

CVE-2026-114386Pydantic AI Harness before 0.59.0 CodeMode Tool Call Limit Bypass via run_code

Medium 4.8

In plain English

A medium-severity resource allocation without limits in pydantic-ai-harness from pydantic. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.3% (higher than 28% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.

Severity (CVSS 3.1)4.8Medium

Exploit odds (30 days)0.3%top 71.7% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official description

Pydantic AI Harness before 0.59.0 fails to enforce UsageLimits.tool_calls_limit on nested tool calls dispatched from run_code in the CodeMode toolset. Users or prompt-injected content can make the sandboxed program invoke tools via run_nested_call() without check_before_tool_call, exceeding operator limits on costly or side-effecting tools.

Affected packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
PyPI	pydantic-ai-harness	0.59.0	GHSA-3589-pxp7-3gj8

Affected products (as reported)

Vendor	Product	Versions
pydantic	pydantic-ai-harness	0 – before 0.59.0

Weakness: CWE-770 · Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L

References

https://github.com/pydantic/pydantic-ai/pull/10362 issue-tracking, patch
https://github.com/pydantic/pydantic-ai/commit/eb27b2b89fe76ae23ee9b6fc9eb4b227a4967949 patch
pydantic-ai-harness v2.59.0 Release Notes release-notes
https://github.com/pydantic/pydantic-ai/blob/v2.58.0/src/pydantic_ai_harness/pydantic_ai_harness/code_mode/_toolset.py#L642-L680 technical-description
https://pypi.org/project/pydantic-ai-harness/0.59.0/ product
VulnCheck Advisory: Pydantic AI Harness before 0.59.0 CodeMode Tool Call Limit Bypass via run_code third-party-advisory