feature-forge
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from users during the discovery and interview phases through interaction. Ingestion points: User responses provided to the AskUserQuestions tool (SKILL.md). Boundary markers: None identified. Capability inventory: Writing specification files to the local specs/ directory. Sanitization: None identified.
- [SAFE]: The skill serves as a structured workflow for product analysis. It does not perform network operations, access sensitive credentials, or execute arbitrary commands.
Audit Metadata