interview
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured guidance for project planning and does not contain instructions for bypassing safety filters, exfiltrating data, or executing unauthorized code.
- [SAFE]: Indirect Prompt Injection Surface Analysis: 1. Ingestion points: The skill reads project specification data from the file path provided in $ARGUMENTS (SKILL.md). 2. Boundary markers: Absent; input content is processed directly. 3. Capability inventory: The skill is permitted to use file manipulation tools (Read, Write, Edit, Glob, Grep) and interaction tools (AskUserQuestion). 4. Sanitization: No input validation or sanitization is performed on the ingested data. However, the logic is limited to asking questions and updating a spec file.
Audit Metadata