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