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 the Read tool.
  • 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) and Read (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
Risk Level
SAFE
Analyzed
Jul 18, 2026, 11:03 AM
Security Audit — agent-trust-hub — meetings-recap