senior-recruiter-simulator
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill is entirely text-based, consisting of Markdown instructions and reference question banks. There are no scripts, binaries, or configuration files that could execute malicious code.
- [PROMPT_INJECTION] (SAFE): The instructions use personas (Sarah, Marcus, etc.) to define behavioral traits for the simulation. These are used for the intended educational purpose and do not attempt to bypass underlying AI safety filters or exfiltrate system prompts.
- [DATA_EXPOSURE] (SAFE): No hardcoded credentials, API keys, or sensitive system paths are present. The skill references its own internal files (e.g., 'references/technical-questions.md') using safe relative paths.
- [INDIRECT_PROMPT_INJECTION] (INFO): The skill is designed to ingest and evaluate user answers during a mock interview. While this constitutes an untrusted data entry point, the skill has no dangerous capabilities (no file writing, no network access, no shell execution), meaning the risk of an injection causing side effects is non-existent.
Audit Metadata