meeting-analyzer
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted meeting transcripts, creating an attack surface for indirect prompt injection.
- Ingestion points: Transcripts in .txt, .md, .vtt, .srt, .docx, and .json formats are read from the user's files during the inventory and normalization phases.
- Boundary markers: Absent. The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the transcript text.
- Capability inventory: The agent uses natural language processing to evaluate speaking dynamics, identify conflict avoidance, count filler words, and assess facilitation quality.
- Sanitization: Absent. There is no mention of filtering or validating transcript content before processing.
Audit Metadata