meeting-insights-analyzer
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to analyze meeting transcripts which are untrusted external inputs, creating a vulnerability surface for indirect prompt injection.\n
- Ingestion points: The instructions in
references/examples.mddirect the agent to scan local folders for transcript files in various formats (.txt, .md, .vtt, .srt, .docx).\n - Boundary markers: The instructions do not define delimiters or provide clear guidelines for the agent to ignore instructions found within the transcript content.\n
- Capability inventory: The skill utilizes the agent's ability to search and read local file system content across multiple documents.\n
- Sanitization: No filtering or validation steps are defined to sanitize the transcript text before it is processed by the LLM.\n- [NO_CODE]: This skill consists purely of markdown documentation and text-based instructions. It does not include any executable scripts, binary files, or tool configurations.
Audit Metadata