Security audit
Security checks across malware telemetry and agentic risk
This is a real benchmarking skill, but it reads detailed local agent session data and automatically serves generated reports in ways users should review before installing.
Install only if you are comfortable with a benchmarking tool that runs target skills for real, consumes tokens, reads detailed local OpenClaw session and transcript artifacts, stores reports/results under ~/.openclaw, and starts a local report server. Use harmless test tasks, avoid secrets or customer data in benchmark prompts, and do not benchmark destructive or account-changing skills without separate safeguards.
url = f"http://localhost:{port}/{filename}"
# 后台启动 python -m http.server，30 秒后自动退出
subprocess.Popen(
["python3", "-m", "http.server", str(port), "--directory", serve_dir],
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,64/64 vendors flagged this skill as clean.
No suspicious patterns detected.