Authorization Flaw in Pydantic AI (CVE-2026-65975)
Summary
Vulnerability in Pydantic AI (CVE-2026-65975). Risk of unauthorized operations or information disclosure.
Original description
The description as published by the source.
Pydantic AI is a Python agent framework for building applications and workflows with Generative AI. In versions 1.88.0 up to but not including 1.107.1 and 2.0.0b1 up to but not including 2.5.0, the UI adapters (AG-UI via Agent.to_ag_ui()/AGUIAdapter, and Vercel AI via VercelAIAdapter) use sanitize_messages to strip unresolved ("dangling") client-submitted tool calls from untrusted message history before it reaches the agent, a defense-in-depth default that prevents the agent from executing tool calls the model never emitted. However, the strip anchored to a message index computed before sanitization ran, so when a trailing client message sanitized to empty and was dropped (for example a client system message under the default manage_system_prompt='server'), a preceding assistant response carrying an unresolved tool call became the new tail and was dispatched without inspection. As a result, a remote client could cause a registered, non-approval server tool to run with client-supplied arguments rather than arguments the model produced. The impact is bounded by what the affected tools do and is most significant for applications that gate tool execution in a model-request hook (before_model_request / after_model_request), since a forged call skips the model turn and bypasses that guardrail; approval-gated tools (requires_approval=True) are not auto-executed by this path. This issue has been fixed in versions 1.107.1 and 2.5.0.
Source: NIST National Vulnerability Database NVD GitHub Advisory
Auto-generated summary
Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.
A vulnerability tracked as CVE-2026-65975 has been found in Pydantic AI.
Risk of unauthorized operations or information disclosure. CVSS score: 6.5/10.
What to do: apply the vendor's official patched release.
If unsure, ask your IT team or search "Pydantic AI CVE-2026-65975" on the vendor's site.
CVE-2026-65975 (Pydantic AI) — CWE-863 / CVSS v3 6.5
Attack vector: remote (network-reachable) / unauthenticated / no user interaction
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.
Incorrect authorization (CWE-863) exists in Pydantic AI.
Check the vendor advisory for the affected versions of Pydantic AI.
Severity: Medium (CVSS 6.5/10). Risk of unauthorized operations or information disclosure.
Update to the patched release per vendor advisory.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. Audit SBOM/dependencies to find affected services.
Response actions
Concrete steps and command examples for SOC/SRE teams to execute in order
-
1Identify exposure identify
Audit SBOM/dependencies for affected components.資産台帳・SBOM・依存マニフェストで Pydantic AI を使っているサービスとバージョンを洗い出す。
-
2Post-deployment verification verify
Confirm patched version is live in productionパッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番ではアクセスログ・WAF でアラート再発が無いか継続監視。
References
- advisory github.com
- advisory github.com
- advisory nvd.nist.gov