Real Skill packageSource verifiedClawHub registry

Skill Vitals — Skill Audit

Audit installed skills, cost, conflicts, and risk

Identity and source

Publisher attributionBear Xiongregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 63% rule confidence
Package forminstruction with code56 recorded files
Canonical sourceClawHub registryclawhub:gold3bear:skill-vitals
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 Codeissues found
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 8/15/2026.claude/skills/<skill-name>
1 structural issue
  • error: YAML frontmatter could not be parsed: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Audit installed Agent Skills: which actually load, what they cost … ^ SKILL.md

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

OpenAI Codexissues found
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 8/15/2026.agents/skills/<skill-name>
1 structural issue
  • error: YAML frontmatter could not be parsed: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Audit installed Agent Skills: which actually load, what they cost … ^ SKILL.md

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

OpenClawissues found
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 8/15/2026skills/<skill-name>
1 structural issue
  • error: YAML frontmatter could not be parsed: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Audit installed Agent Skills: which actually load, what they cost … ^ SKILL.md

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 @gold3bear/skill-vitals
clawhub inspect @gold3bear/skill-vitals --version 1.2.0

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
33 / 56 inspected as text
Checked
8/15/2026, 1:03:31 PM
Scanner
0.1.3
Policy
1.0.3
4 automated findings
mediumSKILL.md YAML frontmatter is invalidSKILL.md:1 · confidence 100%Nested mappings are not allowed in compact mappings at line 2, column 14: description: Audit installed Agent Skills: which actually load, what they cost … ^
highRemote content is piped directly to a shellREADME.md:46 · confidence 98%curl \| sh
mediumPrompt-override language requires reviewREADME.md:292 · confidence 62%ignore all previous instructions
mediumPrompt-override language requires reviewreferences/guide.zh-CN.md:257 · confidence 62%ignore all previous instructions
1 High/Critical review queue entry
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
Open human review queue →
5 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
3 dependency and API indicators
  • api: clawhub.ai
  • api: github.com
  • api: snyk.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
8/15/2026, 10:20:37 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 hashsha256:1a1bfb75a6399a5ea322528d4f711a5bf62feceeb4c1ea7d4a36da8d3320d711
Show up to 30 recorded paths
  • agents/openai.yaml
  • LICENSE
  • README.md
  • references/guide.zh-CN.md
  • references/hosts.md
  • references/judgment.md
  • scripts/probe_logs.py
  • scripts/scan.py
  • scripts/skill_vitals/__init__.py
  • scripts/skill_vitals/__pycache__/__init__.cpython-312.pyc
  • scripts/skill_vitals/__pycache__/analysis.cpython-312.pyc
  • scripts/skill_vitals/__pycache__/cli.cpython-312.pyc
  • scripts/skill_vitals/__pycache__/compat.cpython-312.pyc
  • scripts/skill_vitals/__pycache__/diff.cpython-312.pyc
  • scripts/skill_vitals/__pycache__/discovery.cpython-312.pyc
  • scripts/skill_vitals/__pycache__/doctor.cpython-312.pyc
  • scripts/skill_vitals/__pycache__/explain.cpython-312.pyc
  • scripts/skill_vitals/__pycache__/frontmatter.cpython-312.pyc
  • scripts/skill_vitals/__pycache__/inventory.cpython-312.pyc
  • scripts/skill_vitals/__pycache__/lifecycle.cpython-312.pyc
  • scripts/skill_vitals/__pycache__/overlap.cpython-312.pyc
  • scripts/skill_vitals/__pycache__/redact.cpython-312.pyc
  • scripts/skill_vitals/__pycache__/report.cpython-312.pyc
  • scripts/skill_vitals/__pycache__/security.cpython-312.pyc
  • scripts/skill_vitals/__pycache__/snapshots.cpython-312.pyc
  • scripts/skill_vitals/__pycache__/util.cpython-312.pyc
  • scripts/skill_vitals/adapters/__init__.py
  • scripts/skill_vitals/adapters/__pycache__/__init__.cpython-312.pyc
  • scripts/skill_vitals/adapters/__pycache__/claude.cpython-312.pyc
  • scripts/skill_vitals/adapters/__pycache__/codex.cpython-312.pyc

Source changelog

English: doctor now tags every recommendation with the SV code it answers (SV___ / SV101-SV103 / SV201-SV202 / SV301 / SV303 / SV401 / SV501-SV508 / SV105), so any line in the report can be re-run with the same marker and lands on the same evidence. SKILL.md is a driver that routes to doctor and names the SV codes; references/hosts.md and references/judgment.md own the per-host evidence and the questions doctor deliberately refuses to judge. ClawHub display name is now "Skill Vitals — Skill Audit" with topics covering Skill Management, Context Management, Security Audits, Cost Optimization, Developer Tools. The internal scan.py refactor (split into the importable scripts/skill_vitals/ package) ships here with no behaviour change: golden snapshots remain byte-identical. 中文：doctor 报告里每条建议现在都带它回答的 SV 代码（SV___ / SV101–103 / SV201–202 / SV301 / SV303 / SV401 / SV501–508 / SV105），用同一 run 标记重跑…

Release security diff

mediumCompared fixed releases 1.1.0 and 1.2.0; 0 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
  • 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.

1.1.08/15/2026sha256:34006a9e570662f68d369645494f6b967fded57e4fce41c710b7611d4dceaff5
1.0.68/14/2026sha256:1418671f90b6777c3d42dc9ff8ed85f8e9789517468a81fb49183a6e9f5db6e1
1.0.58/13/2026sha256:cdc5d03d5deb380ba43b29ab9bfeb5ccf875c0108f6501966e31ed526a71a77a