interview-me
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions are entirely focused on conversational logic for requirement gathering. No command execution, network access, or sensitive data exposure was found.
- [INDIRECT_PROMPT_INJECTION]: The skill presents a theoretical surface for indirect prompt injection as it processes raw user input and proposes saving it to the filesystem. Ingestion points: User input received during the Step 2 interview process. Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' markers for user input. Capability inventory: The skill instructions include writing confirmed intent to local files (e.g., docs/intent/). Sanitization: No explicit content filtering or sanitization is described. This is an inherent property of conversational skills and is not indicative of malicious intent.
Audit Metadata