project-scaffolder
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates entirely on local markdown files within a repository to generate project documentation. It does not perform network operations, execute arbitrary code, or access sensitive system paths.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from PRD.md (Ingestion point: SKILL.md Step 1) and interpolates it into documentation that guides future agent behavior. While explicit boundary markers and sanitization are absent, the skill's capabilities are limited to writing local markdown files (Capability inventory: File-write for design.md, AGENTS.md, WORKFLOW.md, and README.md). This behavior is central to the skill's primary purpose and does not represent an active threat.
Audit Metadata