skill-scanner

Solid

Scan, audit, validate, package, or pre-submit AgentSkills using the local BunsDev codeql-sdk/clawhub-audit scanner and OpenClaw skill validation. Use when a user asks to run codeql-sdk, scan a skill before submitting, security-audit a SKILL.md package, produce JSON/SARIF reports, or ensure a skill is ready for Cody/ClawHub handoff.

AI & Automation 36 stars 22 forks Updated today MIT

Install

View on GitHub

Quality Score: 82/100

Stars 20%
52
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Skill Scanner Use this skill for pre-submit scanning and validation of AgentSkills. ## Prime directive Do not call a skill ready until both gates have been attempted: 1. **Skill structure gate** — `openclaw skills check` and/or `package_skill.py` validation. 2. **Security scan gate** — `codeql-sdk` / `clawhub-audit` scan. If CodeQL CLI is missing, report that as a blocker and give the exact install/rerun command. If CodeQL runs but reports no analyzable source code, mark the security scan as `not applicable`, not passed. Do not silently replace the scan with weaker checks. ## Default local paths - SDK repo: `/Users/buns/Documents/GitHub/BunsDev/codeql-sdk` - SDK CLI source: `/Users/buns/Documents/GitHub/BunsDev/codeql-sdk/dist/cli.js` - Skill creator package validator: `~/.nvm/versions/node/v24.13.0/lib/node_modules/openclaw/skills/skill-creator/scripts/package_skill.py` - Workspace skills root: `/Users/buns/.openclaw/workspace/skills` Read `references/codeql-sdk.md` for CLI details, report formats, and troubleshooting. ## Standard scan workflow Given a skill directory: ```bash SKILL_DIR=/absolute/path/to/skill REPORT_DIR="$(dirname "$SKILL_DIR")/.scan-reports/$(basename "$SKILL_DIR")" mkdir -p "$REPORT_DIR" ``` 1. Preflight: ```bash test -f "$SKILL_DIR/SKILL.md" node /Users/buns/Documents/GitHub/BunsDev/codeql-sdk/dist/cli.js version command -v codeql || test -x "$CODEQL_PATH" ``` 2. Validate structure: ```bash openclaw skills check python3 ~/.nvm/versions/n...

Details

Author
OpenCoven
Repository
OpenCoven/coven
Created
3 months ago
Last Updated
today
Language
Rust
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Solid

skill-security-auditor

Security audit and vulnerability scanner for AI agent skills before installation. Use when: (1) evaluating a skill from an untrusted source, (2) auditing a skill directory or git repo URL for malicious code, (3) pre-install security gate for Claude Code plugins, OpenClaw skills, or Codex skills, (4) scanning Python scripts for dangerous patterns like os.system, eval, subprocess, network exfiltration, (5) detecting prompt injection in SKILL.md files, (6) checking dependency supply chain risks, (7) verifying file system access stays within skill boundaries. Triggers: "audit this skill", "is this skill safe", "scan skill for security", "check skill before install", "skill security check", "skill vulnerability scan".

46 Updated 2 days ago
adriannoes
AI & Automation Listed

skill-security-auditor

Security audit and vulnerability scanner for AI agent skills before installation. Use when: (1) evaluating a skill from an untrusted source, (2) auditing a skill directory or git repo URL for malicious code, (3) pre-install security gate for Claude Code plugins, OpenClaw skills, or Codex skills, (4) scanning Python scripts for dangerous patterns like os.system, eval, subprocess, network exfiltration, (5) detecting prompt injection in SKILL.md files, (6) checking dependency supply chain risks, (7) verifying file system access stays within skill boundaries. Triggers: "audit this skill", "is this skill safe", "scan skill for security", "check skill before install", "skill security check", "skill vulnerability scan".

1 Updated today
nariatrip191
AI & Automation Listed

skill-security-audit

Security-audit Agent Skills and plugins — vet a new skill before installing it, scan everything already installed on this machine, or harden your own skill before publishing. Use when asked to vet, review, or check a skill/SKILL.md/plugin for safety, prompt injection, malware, or suspicious behavior — or to make a skill safe to publish.

0 Updated 6 days ago
joshphoenix1