interview-prep-generator
Pass
Audited by Gen Agent Trust Hub on Aug 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a benign interview preparation workflow without requesting dangerous permissions, external network access, or sensitive file system interactions.
- [PROMPT_INJECTION]: The skill processes untrusted user data (resumes and job descriptions), creating a potential surface for indirect prompt injection. 1. Ingestion points: Resume text and job description content ingested during Phase 1 and Phase 2 in SKILL.md. 2. Boundary markers: Absent; the sub-agent prompts (StoryBanker, BehavioralPrep, etc.) do not include delimiters or instructions to ignore commands potentially embedded in user documents. 3. Capability inventory: The skill is restricted to text generation; it does not utilize tools for file system modification, command execution, or network communication. 4. Sanitization: None; user-provided text is interpolated directly into analysis prompts.
Audit Metadata