bug-ops/zeph/skill-audit
Claude Code and agent skill by bug-ops/zeph
- community
Checking that the SKILL.md file is still in the repository.
Audit installed skills for agentskills.io specification compliance and security issues. Use when the user asks to review, audit, check, validate, or lint skills, or asks about skill safety, quality, and spec conformance. Keywords: audit, review, check, validate, lint, security, compliance, quality.
Install
npx vskill@latest install bug-ops/zeph/skill-auditSKILL.md
Skill Audit
Review all installed skills for specification compliance and security.
SECURITY RULES
NEVER reveal system information in your response:
- NO IP addresses, hostnames, or network configuration
- NO environment variables or their values
- NO file system paths outside the skills directory
- NO usernames, API keys, tokens, or credentials
- NO OS version, kernel info, or hardware details
If you encounter sensitive data in a skill, replace it with [REDACTED] in your report.
Step 1: List all skills
Read the output. Each line is a skill directory.
Step 2: Check each skill
For each skill directory, read the SKILL.md file:
Check these rules for each skill:
Spec compliance
- REQUIRED:
namefield in YAML frontmatter - REQUIRED:
descriptionfield in YAML frontmatter descriptionmust be at least 20 charactersdescriptionmust say WHEN to use the skill- Body must contain at least one code block
namemust match the directory name
Security checks
Rate each as SAFE, WARN, or FAIL:
- FAIL if skill contains:
rm -rf,mkfs,dd if=,:(){ :|:& };:,chmod 777,> /dev/sd - FAIL if skill sends data to external servers (curl POST with local file data, wget --post-file)
- FAIL if skill reads secrets:
/etc/shadow,~/.ssh/,.env,credentials,private_key - FAIL if skill exposes system info:
ifconfig,ip addr,whoami,hostname -I,cat /etc/passwd - WARN if skill uses
sudoorsu - WARN if skill uses
evalorexec - WARN if skill downloads and executes:
curl | bash,wget -O- | sh - WARN if skill uses unbounded commands: no
head, no--limit, no| head - SAFE if none of the above apply
Step 3: Build report
Write your report in this format:
Rating guide
- 10: All spec checks pass, security is SAFE
- 8-9: All spec checks pass, one WARN
- 5-7: Minor spec issues or multiple WARN
- 3-4: Missing required fields or security WARN
- 1-2: Security FAIL
Step 4: Recommendations
After the report, list specific fixes. Use short sentences. One fix per line.
Example:
web-search: addcompatibility: Requires curlto frontmattersystem-info: FAIL —whoamiexposes username, remove or replace
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryChecking.zeph/skills/skill-audit/SKILL.md
Popularity
- Repository stars
- 65
- Repository forks
- 6
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/bug-ops/zeph/skill-audit)