Real Skill packageSource verifiedClawHub registryAutomatic security hold

Skill Vetter

OpenClaw 技能自动化审计器 Pro（安全/性能/质量三维度 38 条规则）。基于 spclaudehome v1.0.0 fork 深度升级，新增 JSON 报告、CI 退出码、豁免机制、severity-cap 引擎适配。安装第三方技能前必跑。触发词：vet skill, audit skill, 安全审计, 扫描 skill, skill 检查.

Identity and source

Publisher attributionzuoyunlairegistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 63% rule confidence
Package forminstruction with code13 recorded files
Canonical sourceClawHub registryclawhub:zuoyunlai:lz-skill-vetter-20260819
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/lz-skill-vetter-plus

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

OpenAI Codexpasses with warnings
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/20/2026.agents/skills/lz-skill-vetter-plus
1 structural issue
  • warning: Codex portability follows Agent Skills, where allowed-tools is a space-separated string. SKILL.md

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

OpenClawpasses with warnings
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/20/2026skills/lz-skill-vetter-plus
1 structural issue
  • warning: OpenClaw portability follows Agent Skills, where allowed-tools is a space-separated string. SKILL.md

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

Installation and inspection

Installation commands are hidden while this fixed release is under an automatic security hold. Review the evidence and canonical source manually.

Security evidence

SkillVetAI static result: critical 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
13 / 13 inspected as text
Checked
8/20/2026, 1:18:29 PM
Scanner
0.1.3
Policy
1.0.3
15 automated findings
criticalDestructive command targets a system rootscripts/scan.sh:91 · confidence 98%rm -rf /
highDynamic code or shell execution is presentscripts/scan.sh:87 · confidence 78%exec(
highDynamic code or shell execution is presentassets/report_template.json:26 · confidence 78%eval(
highDynamic code or shell execution is presentreferences/_rules_documentation.md:14 · confidence 78%eval(
highDynamic code or shell execution is presentreferences/audit_protocol.md:45 · confidence 78%eval(
highDynamic code or shell execution is presentreferences/patterns.md:24 · confidence 78%eval(
highDynamic code or shell execution is presentscripts/patterns/red_flags.yml:28 · confidence 78%eval(
highEncoded content is decoded and executedscripts/scan.sh:90 · confidence 90%base64
highEncoded content is decoded and executedreferences/_rules_documentation.md:43 · confidence 90%base64
highEncoded content is decoded and executedreferences/audit_protocol.md:44 · confidence 90%base64
highEncoded content is decoded and executedreferences/patterns.md:53 · confidence 90%base64
highEncoded content is decoded and executedscripts/patterns/red_flags.yml:148 · confidence 90%base64
mediumWorld-writable permissions are requestedreferences/_rules_documentation.md:52 · confidence 95%chmod 777
mediumWorld-writable permissions are requestedreferences/patterns.md:64 · confidence 95%chmod 777
mediumWorld-writable permissions are requestedscripts/patterns/red_flags.yml:191 · confidence 95%chmod 777
12 High/Critical review queue entries
STATIC_DESTRUCTIVE_ROOT_COMMANDpending
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
STATIC_OBFUSCATED_EXECUTIONpending
Open human review queue →
5 inferred permission indicators
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
  • browser control — automatically inferred
3 dependency and API indicators
  • api: api.github.com
  • api: clawhub.ai
  • api: img.shields.io
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
8/20/2026, 3:18:49 AM
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 hashsha256:38a5a243b6bcc66318b8be94eeee6d131e35f1b5e561e97c53f60c252704cf1b
Show up to 13 recorded paths
  • _meta.json
  • assets/report_template.json
  • README.md
  • references/_rules_documentation.md
  • references/audit_protocol.md
  • references/output_format.md
  • references/patterns.md
  • scripts/audit.py
  • scripts/batch_audit.sh
  • scripts/patterns/red_flags.yml
  • scripts/scan.sh
  • skill-card.md
  • SKILL.md

Source changelog

**v2.1.3 closes a severity-cap bypass by enforcing dual-path verdicts and alerting on capped results.** - Audit report now calculates both original and capped severity, always taking the higher as the main verdict. - A warning banner appears in text reports if severity-cap attempted to downgrade the highest finding. - Mitigates bypass where malicious skills set `severity-cap: low` to avoid detection. - Own SKILL.md and workflow unaffected; no regression impacts. - skill-card.md file removed for cleanup.

Release security diff

highCompared fixed releases 2.1.1 and 2.1.3; 3 finding and 0 permission indicators were added.

Both fixed releases were scanned under the current scanner and policy, so finding, permission and dependency changes are available.

Change reasons and limitations
  • new high finding
  • finding surface changed
  • file surface changed
  • content hash changed

Observed release history

These older immutable releases were observed by prior successful syncs. They remain recorded when a newer release becomes current.

2.1.18/19/2026sha256:cbc5083316b4a15be895477ab485d0d213b15de322c63cbc2ae1cc8cae041861