conducting-interviews
Pass
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: LOWNO_CODE
Full Analysis
- NO_CODE (SAFE): The file SKILL.md contains only markdown instructions and natural language guidelines. No scripts (Python, JavaScript, etc.) or executable commands were found within the provided content.
- PROMPT_INJECTION (SAFE): No malicious instructions aimed at overriding agent behavior or bypassing safety filters were detected. All instructions are context-appropriate for the stated purpose of hiring interviews.
- DATA_EXFILTRATION (SAFE): No network-enabled commands (curl, wget) or sensitive file access patterns (SSH keys, environment variables) were identified.
- INDIRECT_PROMPT_INJECTION (INFO): 1. Ingestion: The skill processes user-provided role descriptions and candidate details. 2. Boundary markers: Absent. 3. Capability inventory: No code execution or file-write capabilities exist in the skill. 4. Sanitization: Absent. As the skill lacks dangerous capabilities, the surface for indirect injection is negligible.
Audit Metadata