meeting-insights-analyzer
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process meeting transcripts from various file formats (.txt, .md, .vtt, .srt, .docx), which are untrusted external data sources that could potentially contain instructions to override agent behavior.
- Ingestion points: File scanning operations for transcript content defined in the 'Discover Available Data' section of SKILL.md.
- Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the transcript text.
- Capability inventory: The skill's capabilities are limited to pattern recognition, communication analysis, and providing text-based feedback to the user. It does not possess capabilities for network access, arbitrary file writing, or shell execution.
- Sanitization: There is no mention of sanitizing or validating the contents of the transcript files before the agent processes the text for analysis.
Audit Metadata