Resource exhaustion in Pydantic Pydantic-Ai-Harness
CVE-2026-114386
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.
Published · last modified .
CVSS v3 metric
CVSS v3 base score 4.8 (Medium). Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:N/I:L/A:L.
EPSS exploit prediction
No EPSS score from FIRST.org yet. New CVEs usually get one within a few days; no score means no signal yet, not low risk. How EPSS works.
Affected products
Weakness classification (CWE)
References
- github.com/pydantic/pydantic-ai/pull/10362 (issue-tracking, patch)
- github.com/pydantic/pydantic-ai/commit/eb27b2b89fe76ae23ee9b6fc9eb4b227a4967949 (patch)
- github.com/pydantic/pydantic-ai/releases/tag/v2.59.0 (release-notes)
- github.com/pydantic/pydantic-ai/blob/v2.58.0/src/pydantic_ai_harness/pydantic_a… (technical-description)
- pypi.org/project/pydantic-ai-harness/0.59.0/ (product)
- www.vulncheck.com/advisories/pydantic-ai-harness-before-0.59.0-codemode-tool-ca… (third-party-advisory)
Frequently asked questions
- What is CVE-2026-114386?
- CVE-2026-114386 is a medium-severity vulnerability in Pydantic Pydantic-Ai-Harness, classified under Allocation of Resources Without Limits or Throttling. CVSS score: 4.8/10. Published 2026-10-21.
- How severe is CVE-2026-114386?
- Medium severity. CVSS v3 base score is 4.8 out of 10.