summarize-meeting

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by processing untrusted data from meeting transcripts, recordings, or notes.
  • Ingestion points: The skill reads user-provided meeting transcripts and notes files as mentioned in the instructions of SKILL.md.
  • Boundary markers: There are no delimiters or explicit instructions to the agent to ignore or isolate commands embedded within the input data.
  • Capability inventory: The skill is capable of performing web searches and writing files to the local file system (e.g., Meeting-Summary-[date]-[topic].md).
  • Sanitization: The skill does not perform any validation, escaping, or sanitization of the external input before it is processed into the final summary.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 05:03 AM