Skill Trust Guard

Enforces skill-trust-scanner security checks before installing skills, blocking or alerting based on risk scores to reduce supply chain threats.

This package implements exactly what it says (wraps 'clawhub install' and runs a scanner) but contains a couple of red flags you should address before using it: (1) it expects a scanner at a hard-coded developer path (/home/guofeng/...), so by default it will fail on most machines or — if that path exists — run whatever code is there; (2) the pre-install hook uses 'npx tsx' which can fetch and run code from npm at runtime; (3) integrate.sh installs a PATH shim that will intercept all future 'clawhub install' calls. Recommended steps before installing/integrating: inspect the scanner CLI source you plan to point to (set SCANNER_ROOT/SCANNER_CLI to a trusted local copy or a vetted release), run install.sh on a harmless local skill to observe behavior, avoid running integrate.sh until you trust the scanner (or back up your clawhub binary path), and prefer bundling or referencing a released scanner package (GitHub release or published npm package) rather than relying on a hard-coded developer path. If you want a safer posture, ask the author for a packaged scanner dependency or a verified install mechanism.

Type: OpenClaw Skill Name: skill-trust-guard Version: 1.0.0 The skill-trust-guard is designed as a security measure to scan and block malicious OpenClaw skills, as evidenced by its stated purpose and test reports (TEST_REPORT.md explicitly mentions blocking skills that 'read ~/.clawdbot/.env + exfiltrate to a malicious domain'). However, it is classified as 'suspicious' due to its critical reliance on an external, unprovided 'skill-trust-scanner' (hardcoded path in hooks/pre-install.sh: /home/guofeng/clawd/skill-trust-scanner/src/cli.ts), making its core security logic a black box. Furthermore, the install.sh script performs actions like 'git clone' and 'clawhub install' (for temporary fetching) *before* the skill is fully scanned, which could expose the system to pre-scan execution risks (e.g., git hooks or clawhub pre-install scripts from untrusted skills).