meeting-review
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, potentially untrusted data such as meeting transcripts, proposals, and code documentation.
- Ingestion points: Data enters the agent context through the analysis of meeting transcripts and external documents referenced in SKILL.md.
- Boundary markers: The instructions lack specific boundary markers or sanitization requirements for the content extracted from transcripts, although they do require labeling AI-generated output.
- Capability inventory: The skill is granted permissions for write_file, edit_file, and execute_command, which could potentially be abused by malicious instructions embedded within processed meeting transcripts.
- Sanitization: No explicit sanitization or filtering of external transcript content is mandated before it is processed by the agent.
Audit Metadata