expert-interview
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it collects unstructured user input (interview responses) intended for use as context in downstream writing tasks.
- Ingestion points: User-provided topics and interview answers in SKILL.md.
- Boundary markers: The skill lacks instructions to wrap user-provided data in delimiters or warnings to prevent downstream agents from executing embedded instructions.
- Capability inventory: The resulting 'knowledge document' is designed to be fed into 'write-content' or 'improve-content' skills.
- Sanitization: There is no evidence of filtering or sanitization of user input before it is included in the output artifact.
Audit Metadata