core-interview
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for requirement gathering through user interviews. It does not contain any executable scripts, configuration files, or external code.
- [SAFE]: No credentials, sensitive file paths, or network exfiltration patterns were detected.
- [SAFE]: There are no remote downloads or unverifiable dependencies. All logic is contained within the prompt instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a loop for ingesting external data. 1. Ingestion points: User-provided answers and codebase content. 2. Boundary markers: No explicit delimiters defined. 3. Capability inventory: No dangerous tools such as file-write, network access, or shell execution are defined within the skill. 4. Sanitization: No explicit sanitization is performed. The lack of dangerous capabilities mitigates the risk from untrusted input.
Audit Metadata