CVE-2026-65975 Pydantic AI AG-UI Adapter: A dangling client-submitted tool call can execute when a trailing message is dropped during `sanitize_messages`
- Published
- Updated
- Exploit status
- No public exploit known
- CISA SSVC
- No known exploitation · automatable: yes · technical impact: partial
- Technology
- Red Hat
Description
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.
Upgrade path
4 packages: 1 fixed, 1 with no fix yet.
| Package | Affected | Fixed in | Status |
|---|---|---|---|
| redhat/lightspeed-core/lightspeed-stack-rhel9(Red Hat lightspeed_core) | All versions | No fix listed | No fix yet |
| pydantic ai | >= 1.88.0, < 1.107.1; >= 2.0.0, < 2.5.0 | 1.107.1, 2.5.0 | Fixed |
| pydantic-ai | = >= 1.88.0, < 1.107.1; = >= 2.0.0b1, < 2.5.0 | No fix listed | Versions listed |
| pydantic-ai-slim | = >= 1.88.0, < 1.107.1; = >= 2.0.0b1, < 2.5.0 | No fix listed | Versions listed |
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| pydantic-ai | = >= 1.88.0, < 1.107.1 | No fix listed |
| pydantic-ai | = >= 2.0.0b1, < 2.5.0 | No fix listed |
| pydantic-ai-slim | = >= 1.88.0, < 1.107.1 | No fix listed |
| pydantic-ai-slim | = >= 2.0.0b1, < 2.5.0 | No fix listed |
| redhat/lightspeed-core/lightspeed-stack-rhel9(Red Hat:lightspeed_core) | All versions | No fix listed |
| pydantic ai | >= 1.88.0, < 1.107.1 | 1.107.1 |
| pydantic ai | >= 2.0.0, < 2.5.0 | 2.5.0 |
References
- https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-jpr8-2v3g-wgf9 vendor-advisory
- Red Hat CVE page mitigation vendor-advisory
- Red Hat Bugzilla 2508670 issue-tracking
- www.cve.org
- nvd.nist.gov