amose
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and synthesize domain-specific information from project files (source code, tests, and configuration). While this involves ingesting external data, the skill specifies clear boundary markers and verification steps (e.g., concrete scenarios to distinguish concepts) to ensure semantic consistency rather than executing instructions found within that data. The lack of network or system-level capabilities further mitigates this risk.
Audit Metadata