interview
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a well-structured instructional prompt that guides the AI to ask deep, non-obvious questions. It follows best practices for user interaction, such as asking one question at a time and challenging assumptions. No malicious behavior, such as data exfiltration or persistence mechanisms, was detected.
- [PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection because it reads file content provided by the user ($0) to use as context for the interview. While this is a primary feature of the skill, it lacks explicit boundary markers for the ingested data.
- Ingestion points: File paths or topic descriptions provided in the input argument (SKILL.md).
- Boundary markers: Absent.
- Capability inventory: Reading local file context and using the AskUserQuestion tool for user interaction.
- Sanitization: Absent; the skill does not explicitly sanitize or delimit the content read from files before processing.
Audit Metadata