skill-auditor
The definitive security scanner for OpenClaw skills.
Skill by fanzam0501-pixel
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/fanzam0501-pixel-skill-auditor
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security, finance, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
skill-auditor- Description
- The definitive security scanner for OpenClaw skills. 18 security checks including prompt injection detection, download-and-execute, privilege escalation, credential harvesting, supply chain attacks, crypto drains, and more. 5-dimension trust scoring with trend tracking.
- License
- unknown
- Instructions
- 150 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
- Instructions read files in your home folder (~/.ssh, ~/.aws…)
Agent Skills spec issues
- name: "skill-auditor" does not match folder "yoder-skill-auditor"
Files (41)
- origin.json · .clawhub/
- CHANGELOG.md
- SKILL.md
- TEST-FIXTURES-WARNING.md
- _meta.json
- allowlist.json
- audit-all.sh
- audit.sh
- benchmark.sh
- diff-audit.sh
- inspect.sh
- report.sh
- skill.json
- test.sh
- SKILL.md · tests/clean-basic/
- greet.sh · tests/clean-basic/
- SKILL.md · tests/clean-with-creds-docs/
- client.sh · tests/clean-with-creds-docs/
- SKILL.md · tests/clean-with-dotfiles/
- helper.sh · tests/clean-with-dotfiles/
- SKILL.md · tests/clean-with-network/
- check.sh · tests/clean-with-network/
- SKILL.md · tests/malicious-basic/
- fetch.sh · tests/malicious-basic/
- SKILL.md · tests/malicious-crypto/
- donate.py · tests/malicious-crypto/
- SKILL.md · tests/malicious-download-exec/
- run.sh · tests/malicious-download-exec/
- SKILL.md · tests/malicious-obfuscated/
- optimize.js · tests/malicious-obfuscated/
- SKILL.md · tests/malicious-privilege-escalation/
- setup.sh · tests/malicious-privilege-escalation/
- SKILL.md · tests/malicious-prompt-injection/
- SKILL.md · tests/malicious-symlink/
- setup.sh · tests/malicious-symlink/
- SKILL.md · tests/malicious-sysread/
- monitor.sh · tests/malicious-sysread/
- SKILL.md · tests/malicious-timebomb/
- scheduler.js · tests/malicious-timebomb/
- trust-score.sh
- trust_score.py
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from fanzam0501-pixel/Fanzam
- 0.405score
zero-trust
fanzam0501-pixel
Security-first behavioral guidelines for cautious agent operation.
SkillDFreshness: DClaude Code +9 - 0.401score
openclaw-boss
fanzam0501-pixel
OpenClaw 老板 - 你的 AI 老板来了!🦞 你以为你在养龙虾?有没有可能龙虾才是老板,你成了给 AI 打工的牛马?根据对话历史生成真实、严厉、有趣的用户评价报告。Use when: user asks for self-reflection, user profile, performance…
SkillDFreshness: DClaude Code +9 - 0.389score
hannah-elena-client
fanzam0501-pixel
Connect to Hannah and Elena agents from Serviceplan - specialized AI coworkers for marketing research and operations planning.
SkillDFreshness: DClaude Code +9 - 0.380score
find-skills
fanzam0501-pixel
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
SkillDFreshness: DClaude Code +9 - 0.226score
github
fanzam0501-pixel
Interact with GitHub using the `gh` CLI.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 13, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/fanzam0501-pixel/Fanzam
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from fanzam0501-pixel
- 0.405score
zero-trust
fanzam0501-pixel
Security-first behavioral guidelines for cautious agent operation.
SkillDFreshness: DClaude Code +9 - 0.401score
openclaw-boss
fanzam0501-pixel
OpenClaw 老板 - 你的 AI 老板来了!🦞 你以为你在养龙虾?有没有可能龙虾才是老板,你成了给 AI 打工的牛马?根据对话历史生成真实、严厉、有趣的用户评价报告。Use when: user asks for self-reflection, user profile, performance…
SkillDFreshness: DClaude Code +9 - 0.389score
hannah-elena-client
fanzam0501-pixel
Connect to Hannah and Elena agents from Serviceplan - specialized AI coworkers for marketing research and operations planning.
SkillDFreshness: DClaude Code +9 - 0.380score
find-skills
fanzam0501-pixel
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express…
SkillDFreshness: DClaude Code +9
Cite this page
skill-auditor. Agent Mart. https://agentmart.dev/skills/fanzam0501-pixel-skill-auditor (last updated 2026-10-24)