interview-me
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input during a multi-turn interview to generate research specifications and decision records. This input is also passed to a subagent for citation verification.
- Ingestion points: User input enters the system via the initial topic argument and subsequent responses throughout the six-phase interview defined in SKILL.md.
- Boundary markers: The skill does not explicitly define delimiters or use 'ignore embedded instructions' prompts when interpolating user content into the research spec or subagent tasks.
- Capability inventory: The skill uses the 'Write' tool to create files in the 'quality_reports/' directory and the 'Agent' tool to spawn a 'claim-verifier' subagent.
- Sanitization: The skill includes a 'sanitized_topic' placeholder for generated filenames to prevent path traversal, although it does not define specific sanitization logic for the content of the generated markdown files.
Audit Metadata