mock-interview
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a standard conversational agent implementation for role-playing an interview coach. No suspicious command execution, file system access, or network calls were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user input during interview simulations.
- Ingestion points: User responses provided during the interactive interview session defined in SKILL.md.
- Boundary markers: Absent; the skill relies on conversational context rather than explicit delimiters (e.g., XML tags) to separate instructions from user input.
- Capability inventory: No capabilities detected. The skill does not utilize any tools for file system access, network operations, or subprocess execution.
- Sanitization: Absent; no explicit sanitization of user input is performed before the agent processes it.
- Assessment: Because the skill lacks sensitive tool access, the potential for exploitation via indirect prompt injection is negligible.
Audit Metadata