functional-design
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWSAFE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill processes untrusted external content, creating a surface for potential instruction injection. Ingestion points: Reads from
docs/product-requirements.md. Boundary markers: None detected in instructions. Capability inventory: Local file system write todocs/functional-design.md. Sanitization: None specified for input content. - [General] (SAFE): No evidence of command execution, network exfiltration, hardcoded credentials, or obfuscation was found in the skill definition.
Audit Metadata