CVE detail
CVE-2026-65975
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.
Buzz score
Why this CVE is surfacing
This all-time snapshot uses the same composite formula as Trending across a 30-year evidence window, rather than a current rolling window.
Buzz score components · mention 6.9 · diversity 5.0 · KEV 0.0 · OTX 0.0 · PoC 0.0
Why it matters now
Mention timeline
- Total mentions
- 1
- within the 30d window
- Peak daily
- 1
- highest bucket
Evidence
Source links by recency
1 source links · newest first
No excerpt available.
Exploitgithub.comJul 29, 2026, 9:17 PM
Exploit code
Public exploit repository references
Public PoC repositories are third-party, potentially unsafe artifacts. Treat their code as untrusted and use it only on authorized systems in an isolated, least-privilege environment. cvebuzz does not execute the code or verify that an exploit works.
0 repository references · best confidence N/A · max 0 stars
Related records
Similar CVEs
6 related CVEs with shared weakness or product evidence
- CVE-2026-67347CVSS 6.1 · Medium
Vendure through 3.7.1, fixed in commit f67ef5f, contains a cross-channel authorization bypass vulnerability in stock-location.service.ts and asset.service.ts update methods that a…
- CVE-2026-41187CVSS 6.2 · Medium
Calico's apiserver wraps tier-scoped resources so that every operation runs through AuthorizeTierOperation, but the Delete override on NetworkPolicy, GlobalNetworkPolicy, and thei…
- CVE-2026-14923CVSS 6.5 · Medium
The Sync Post With Other Site WordPress plugin before 1.9.3 does not correctly enforce the page-editing capability on a REST route that creates and updates posts, because of an op…
- CVE-2026-48449CVSS 10.0 · Critical
Adobe Campaign Classic (ACC) is affected by an Incorrect Authorization vulnerability that could result in arbitrary code execution in the context of the current user. Exploitation…
- CVE-2026-67439CVSS 4.3 · Medium
OliveTin gives safe and simple access to predefined shell commands from a web interface. Prior to 3000.17.0, the service/internal/api/api.go StartActionAndWait and StartActionByGe…
- CVE-2026-6336CVSS 5.3 · Medium
GitLab has remediated an issue in GitLab CE/EE affecting all versions from 16.6 before 19.0.5, 19.1 before 19.1.3, and 19.2 before 19.2.1 that under certain conditions could have…