Skill Defender

Scans installed OpenClaw skills for malicious patterns including prompt injection, credential theft, data exfiltration, obfuscated payloads, and backdoors. Use when installing new skills, after skill updates, or for periodic security scans. Runs deterministic pattern matching — fast, offline, no API cost.

This skill appears internally consistent: it's an offline, deterministic pattern scanner implemented in Python that reads skill directories and reports findings. Before installing or running it, consider these points: (1) Source provenance — the skill's owner and homepage are unknown; prefer code from a trusted publisher or review the code yourself. (2) Local file access — the scanner will read all files in your skills directory (which is necessary for scanning). If your skills contain sensitive secrets, consider auditing those files separately or run the scanner in a controlled environment. (3) Allowlist/false positives — the tool includes a built-in allowlist that can suppress findings; review that allowlist to ensure it isn’t silencing legitimate issues. (4) No network I/O is visible in the provided code, but always review the full scripts before running. If you cannot inspect the code, run it in a sandboxed environment or a VM and verify behavior (stdout, exit codes) on a non-production copy of your skills directory.

Type: OpenClaw Skill Name: skill-defender Version: 1.0.0 The 'skill-defender' skill is a security scanner designed to detect malicious patterns like prompt injection, RCE, and credential theft. Its documentation (SKILL.md, references/threat-patterns.md) and core scanning script (scripts/scan_skill.py) necessarily contain examples and regexes of these malicious patterns. The skill explicitly states it will flag itself without an allowlist, which is implemented in scripts/aggregate_scan.py. All file system access and subprocess execution are aligned with its stated purpose of scanning other skills, with no evidence of intentional harmful behavior or prompt injection against the agent itself.