Baitaphish
Security intelligence
SearchLatest briefing
CVE Explorer

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
Lifecycle PUBLISHED1 preserved revisionFact urn:baitaphish:canonical-cve-fact-revision:v2:e5325a8fa6a2271982e748d6ccb949cbce6f7c3315bf0a3a2fb1b9668a9ca071
Known exploited
Not asserted
Disputed
No
Stale source
No
Conflicts
1

Preserved source conflicts

No provider value was silently selected as the winner.

affected · 2 assertions

{"product":"pydantic-ai-slim","vendor":"pydantic","versions":[{"status":"affected","version":">= 1.88.0, < 1.107.1"},{"status":"affected","version":">= 2.0.0b1, < 2.5.0"}]}

  • cve_program_cvelist_v5affected
    urn:baitaphish:normalized-source-record:v2:0cb60f69fb7baadd4520e1b468dd2606127aac36cbe6f8455998e67afad2e977 · sha256:eed06c6273f74b49… · /containers/cna/affected/1

{"product":"pydantic-ai","vendor":"pydantic","versions":[{"status":"affected","version":">= 1.88.0, < 1.107.1"},{"status":"affected","version":">= 2.0.0b1, < 2.5.0"}]}

  • cve_program_cvelist_v5affected
    urn:baitaphish:normalized-source-record:v2:0cb60f69fb7baadd4520e1b468dd2606127aac36cbe6f8455998e67afad2e977 · sha256:eed06c6273f74b49… · /containers/cna/affected/0

Affected products and versions

2 source assertions
{"product":"pydantic-ai-slim","vendor":"pydantic","versions":[{"status":"affected","version":">= 1.88.0, < 1.107.1"},{"status":"affected","version":">= 2.0.0b1, < 2.5.0"}]}
  • cve_program_cvelist_v5affected
    urn:baitaphish:normalized-source-record:v2:0cb60f69fb7baadd4520e1b468dd2606127aac36cbe6f8455998e67afad2e977 · sha256:eed06c6273f74b49… · /containers/cna/affected/1
{"product":"pydantic-ai","vendor":"pydantic","versions":[{"status":"affected","version":">= 1.88.0, < 1.107.1"},{"status":"affected","version":">= 2.0.0b1, < 2.5.0"}]}
  • cve_program_cvelist_v5affected
    urn:baitaphish:normalized-source-record:v2:0cb60f69fb7baadd4520e1b468dd2606127aac36cbe6f8455998e67afad2e977 · sha256:eed06c6273f74b49… · /containers/cna/affected/0

Provider-owned CVSS observations

1 source assertion
{"metric":{"attackComplexity":"LOW","attackVector":"NETWORK","availabilityImpact":"NONE","baseScore":6.5,"baseSeverity":"MEDIUM","confidentialityImpact":"LOW","integrityImpact":"LOW","privilegesRequired":"NONE","scope":"UNCHANGED","userInteraction":"NONE","vectorString":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N","version":"3.1"},"metric_type":"cvssV3_1"}
  • cve_program_cvelist_v5cvss
    urn:baitaphish:normalized-source-record:v2:0cb60f69fb7baadd4520e1b468dd2606127aac36cbe6f8455998e67afad2e977 · sha256:eed06c6273f74b49… · /containers/cna/metrics/0/cvssV3_1

CWE assertions

1 source assertion
{"cweId":"CWE-863","description":"CWE-863: Incorrect Authorization","lang":"en","type":"CWE"}
  • cve_program_cvelist_v5cwe
    urn:baitaphish:normalized-source-record:v2:0cb60f69fb7baadd4520e1b468dd2606127aac36cbe6f8455998e67afad2e977 · sha256:eed06c6273f74b49… · /containers/cna/problemTypes/0/descriptions/0

Source references

1 source assertion
{"name":"https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-jpr8-2v3g-wgf9","tags":["x_refsource_CONFIRM"],"url":"https://github.com/pydantic/pydantic-ai/security/advisories/GHSA-jpr8-2v3g-wgf9"}
  • cve_program_cvelist_v5reference
    urn:baitaphish:normalized-source-record:v2:0cb60f69fb7baadd4520e1b468dd2606127aac36cbe6f8455998e67afad2e977 · sha256:eed06c6273f74b49… · /containers/cna/references/0

Attribution and limitations

  • CVE Program CVEList V5: Reproduce the MITRE copyright designation and CVE license in copies. Source →

Provider severity values are preserved separately. Baitaphish does not convert them into a risk rating, infer affected products, or treat EPSS as observed exploitation.

← Back to CVE Explorer