Medium severity · published Oct 21, 2026
CVE-2026-114386
Pydantic AI Harness before 0.59.0 CodeMode Tool Call Limit Bypass via run_code
New
4.8
CVSS
0.3%
EPSS
No
On KEV
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.
CVSS vector
CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L
Attack vector
Network
Complexity
High
Privileges
None
User interaction
None
Confidentiality
None
Integrity
Low
Availability
Low
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.3% · higher than 28% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
PY
pydantic-ai-harness · pydantic
before 0.59.0 · source: vendor
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-114386
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-114386
github.com
https://github.com/pydantic/pydantic-ai/blob/v2.58.0/src/pydantic_ai_harness/pydantic_ai_harness/code_mode/_toolset.py#L642-L680
github.com
https://github.com/pydantic/pydantic-ai/commit/eb27b2b89fe76ae23ee9b6fc9eb4b227a4967949
github.com
https://github.com/pydantic/pydantic-ai/pull/10362
github.com
https://github.com/pydantic/pydantic-ai/releases/tag/v2.59.0
pypi.org
https://pypi.org/project/pydantic-ai-harness/0.59.0/
www.vulncheck.com
https://www.vulncheck.com/advisories/pydantic-ai-harness-before-0.59.0-codemode-tool-call-limit-bypass-via-run-code