Skip to content
CVE Ledger
  • Newest CVEsPage
  • Recently added to KEVPage
  • Rising exploitation (EPSS)Page
  • Weekly digestPage
  • StatisticsPage
  • WatchlistPage
  • API docsPage
  • MCP serverPage
  • AboutPage
  • Data sourcesPage
  • Data statusPage
  • ChangelogPage
  • How it's builtPage
  • Support the projectPage

14 results

Back

CVE-2026-65975Pydantic AI AG-UI Adapter: A dangling client-submitted tool call can execute when a trailing message is dropped during `sanitize_messages`

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.

Timeline

  1. ID reserved

    By GitHub_M

  2. · 6 days later

    Published

  3. · 1 day later

    Record updated

Changes after publication (a new score, a public exploit, EPSS crossing 1, 10 or 50 %, leaving KEV) are kept since November 2026; earlier ones are not known.

Scores

CVSS scores of CVE-2026-65975, by who scored it
Scored byCVSSScoreVector
GitHub_MCNA (assigner)3.1Medium6.5CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N
NVDNVD · Analyzed3.1Medium6.5CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N
EPSS (exploitation in 30 days)
0.33% · top 74% of all CVEs (16 Nov 2026)
CISA SSVC
Exploitation: none · Automatable: yes · Technical impact: partial
Loading the EPSS history…

The list uses the assigner's score when there is one, then CISA's, then NVD's: Medium 6.5.

Affected products

References

References1

Sources

The same CVE in the primary databases and aggregators, to check against.

Badge for a README or a ticket

CVE-2026-65975 badge
[![CVE-2026-65975](https://cveledger.app/badge/CVE-2026-65975.svg)](https://cveledger.app/cve/CVE-2026-65975)

Record last updated .