Recruiting Interview Kit

根据 JD 生成面试题、评分维度、红旗项与面试记录模板。；use for recruiting, interview, hiring workflows；do not use for 生成歧视性问题, 替代最终录用决策.

This skill appears to do what it claims (generate interview questions/scorecards) and only requires python3, but take these precautions before running: 1) Inspect SKILL.md and other files for invisible/control characters and remove them; the pre-scan flagged unicode control chars. 2) Review scripts/run.py yourself (it's included) to confirm behavior — it only reads local files and writes output, but it will traverse and read any directory you pass as --input. Never run it against root/home or other sensitive paths. 3) Prefer running with --dry-run and using the included example input first, or run inside an isolated/sandbox environment. 4) If you don't want local file access, avoid executing the script and instead ask the skill to produce output based only on the provided JD text/template. 5) If you plan to give the skill directory inputs, sanitize them and avoid passing files that contain secrets or credentials.

Type: OpenClaw Skill Name: recruiting-interview-kit Version: 1.0.0 The bundle contains a script (scripts/run.py) with capabilities that significantly deviate from its stated purpose of generating recruiting interview kits. The script includes a 'pattern_report' function with regex patterns designed to find API keys, tokens, and dangerous shell commands (e.g., curl|bash, base64 execution), as well as functions for recursive directory scanning and CSV data sampling. While the code includes logic to mask discovered secrets and appears to be a security auditing tool, its inclusion in a non-security bundle is a functional discrepancy that provides the agent with tools to identify sensitive data on the host system.