write-feature-prd
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized commands were found in the skill instructions or reference files.
- [PROMPT_INJECTION]: The skill analyzes codebase content which serves as an ingestion point for potentially untrusted data. The risk is evaluated as safe because the skill's capabilities are limited to text generation. Ingestion points: Reads codebase content via /find-code and /code-graph in SKILL.md. Boundary markers: Absent. Capability inventory: No system-level or network capabilities present. Sanitization: Absent.
Audit Metadata