skill-security-scanner
par steffano198
Coding Agents & IDEsRésumé
Scan OpenClaw skills for security issues, suspicious permissions, and trust scoring.
Description
Ce que fait ce skill
Scans OpenClaw skills for security issues, suspicious code patterns, and excessive permissions. Produces a trust score from 0 to 100 based on author reputation, permission scope, and code analysis to help users decide whether a skill is safe to install or run.
Structured trust scoring with weighted criteria replaces manual code review, making security decisions faster and more consistent across skills.
Quand l'utiliser
- Checking a new ClawHub skill before installing it
- Running a weekly audit of all installed skills
- Getting a quick trust score for an unfamiliar skill
- Investigating a skill after a security incident in the ecosystem
- Reviewing permissions requested by a skill before execution
Exemple de workflow
User asks: Is this skill from ClawHub safe to install?
- 1
Runs scan-skill on the skill's local path
- 2
Analyzes frontmatter metadata for requested bins and environment variables
- 3
Checks SKILL.md content for suspicious patterns like network exfiltration, credential access, or obfuscated commands
- 4
Calculates trust score weighted by author reputation, permission scope, code patterns, update frequency, and download count
- 5
Returns a formatted scan result with issues by severity and a recommendation
Trust score report showing score out of 100, list of permissions requested, flagged issues with severity levels, and a clear install or skip recommendation
Installation
clawhub install steffano198/skill-security-scannerExécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.