meeting-summary
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). This skill explicitly ingests arbitrary user-provided meeting records (see SKILL.md: "根据用户提供的会议记录") which are untrusted, user-generated content that the agent reads and interprets to produce summaries, creating a clear avenue for indirect prompt injection.
Audit Metadata