skill-trust-auditor

Audit a ClawHub skill for security risks BEFORE installation.

This skill appears to do what it claims: fetch skill files and run pattern checks. Before installing: (1) review patterns.json if you want to understand what it flags and the allowlisted domains; (2) be aware that enabling '--llm' mode will send snippets to Anthropic if you set ANTHROPIC_API_KEY (only enable if you trust that service); (3) running setup.sh will pip-install packages (requests, anthropic) — inspect the setup script and installed packages if you must maintain a strict supply-chain policy; (4) the auditor fetches remote skill files over the network to analyze them — this network access is necessary but means the tool can only be as accurate as the sources it fetches. Overall, the package is coherent and reasonable for an auditor, but exercise standard caution when enabling LLM judgement or when allowing pip installs on sensitive hosts.

Type: OpenClaw Skill Name: skill-trust-auditor Version: 1.1.3 The OpenClaw skill-trust-auditor is designed to identify security risks in other skills. Its own implementation demonstrates a strong focus on security, including robust input validation and sanitization (e.g., `_sanitize_untrusted` in `scripts/analyze_skill.py`) to prevent prompt injection when using LLMs. Shell commands in `scripts/audit.sh` correctly quote user input, mitigating shell injection risks. The skill's dependencies are standard, and there is no evidence of data exfiltration, backdoor installation, or other malicious intent within its own code or instructions. All identified high-risk patterns are part of its detection logic (`scripts/patterns.json`), not actions performed by the skill itself.