summarize-meeting
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, specifically meeting transcripts, recordings, and notes. This functionality presents an inherent attack surface where malicious instructions embedded in the provided meeting content could attempt to influence the agent's behavior during the summarization process. This is an architectural risk associated with the skill's primary purpose.
- [NO_CODE]: The skill does not include any executable scripts, binaries, or complex automation logic, relying entirely on natural language instructions and structured templates.
Audit Metadata