interview-style-doc-building
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows a predictable loop of user interaction and file updates, requiring explicit user input for every change made to the document.
- [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by taking user answers and writing them directly into local files without sanitization. This is noted as a design feature for its intended purpose.
- Ingestion points: User answers during the interview loop described in SKILL.md.
- Boundary markers: Absent; user input is patched directly into designated sections.
- Capability inventory: Local file system modification using write_file and patch tools.
- Sanitization: No input validation or escaping is applied to the user's responses.
Audit Metadata