Skulk Skill Scanner

Scan OpenClaw skill folders for security red flags before installing or publishing. Detects data exfiltration, credential theft, prompt injection, destructiv...

This scanner appears to be what it claims: a static pattern-based skill scanner. Before trusting its results, run it in a sandbox or on a copy of the skill directory (not on system roots), and: (1) run it with --include-self to self-audit the scanner; (2) manually review any FAIL/WARN findings (static checks produce false positives and false negatives); (3) inspect and if needed customize SAFE_DOMAINS to match your environment; (4) remember it is static-only — it cannot detect runtime-generated exfiltration or sophisticated obfuscation, so follow up with manual review and, for high-risk skills, runtime monitoring in an isolated environment prior to granting sensitive credentials or deployment.

Type: OpenClaw Skill Name: skulk-skill-scanner Version: 1.0.1 The 'skulk-skill-scanner' skill is a static analysis tool designed to identify security risks in other OpenClaw skills. Its core logic in `scripts/scanner.js` reads file contents and matches them against a comprehensive set of patterns for data exfiltration, credential access, prompt injection, destructive commands, and other malicious indicators. The scanner itself does not perform any high-risk actions like network requests, arbitrary file system writes, command execution, or attempts to manipulate the agent via prompt injection. Its behavior is entirely consistent with its stated purpose as a security auditing tool.