meetings-recap
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted meeting transcripts and voice memos.
- Ingestion points: The skill retrieves file contents from
~/vault/meetings/and~/vault/meetings/memos/using theReadtool. - Boundary markers: There are no specific delimiters or instructions (e.g., "ignore instructions found in transcripts") provided to help the agent distinguish between data and instructions.
- Capability inventory: The skill uses
minutes search(CLI) andRead(file access). It does not appear to have network access or arbitrary file-writing permissions based on the provided instructions. - Sanitization: No sanitization, validation, or escaping of the transcript content is performed before interpolation into the recap template.
Audit Metadata