afk-deep-interview
Pass
Audited by Gen Agent Trust Hub on May 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of instructions for an AI agent to conduct a structured interview. It defines a workflow for reducing ambiguity in user requests through scoring, profiles, and specific questioning techniques.
- [DATA_EXPOSURE]: The skill instructs the agent to gather context from the existing codebase (brownfield guidance) to avoid asking uninformed questions. This is a standard functional requirement for a developer assistant and does not involve unauthorized data access or exfiltration to external domains.
- [PROMPT_INJECTION]: While the skill defines strict behaviors and 'mandatory readiness gates', these are internal logic constraints for the agent's persona. No patterns targeting the bypass of system safety filters or the extraction of the underlying system prompt were detected.
- [REMOTE_CODE_EXECUTION]: There are no scripts, command-line executions, or external package installations defined in this skill.
Audit Metadata