Skill

Security audit tool for ClawHub skills. Scans a skill directory with 65 detection patterns, anti-obfuscation analysis, and dual rating system (Security + Com...

This tool appears to do what it says: it reads a skill directory and flags dangerous patterns. Before using it, keep in mind: (1) it will read every file you point it at — don't scan directories that contain private keys or secrets you don't want loaded by a third-party script; run the scanner in an isolated/sandboxed environment if you are unsure. (2) The scanner intentionally suppresses or reduces severity for patterns inside strings, docs, and pattern-definition blocks (to avoid false positives). That behavior is reasonable for a scanner, but it can be abused by a malicious author who formats dangerous code to look like a pattern definition or comment — treat its 'A'/'B' grade as a starting point and manually inspect any high-sensitivity items the scanner flags, especially undeclared permissions (gateway, write, nodes, edit, etc.). (3) Reports embedded in the package appear to be snapshots (older version numbers in reports); prefer running the bundled scanner yourself rather than relying on packaged reports. Overall: the package is coherent with its purpose, but do manual review and run it in a safe environment when scanning untrusted skill directories.

Type: OpenClaw Skill Name: skill-shield Version: 0.6.1 The OpenClaw AgentSkills skill-shield is a security audit tool designed to scan other skills for dangerous patterns. Its `scan.py` code implements robust detection logic, including anti-obfuscation analysis and extensive context-aware false positive reduction mechanisms (e.g., ignoring its own pattern definitions, reducing severity for code in comments/documentation). The `SKILL.md` clearly describes its legitimate security purpose and usage, without any hidden prompt injection commands. While the provided `reports/report.json` and `reports/report.md` show an older version of the scanner (v0.2.0) flagging itself with a 'D' rating due to an undeclared permissions and a false positive `base64_decode` finding, this reflects the scanner's transparency and the developers' subsequent improvements (v0.6.1) to reduce such false positives, rather than malicious intent. The skill's functionality is entirely aligned with its stated purpose of security auditing, with no evidence of data exfiltration, unauthorized execution, or persistence.