Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 9/20/2026.claude/skills/huawei-cloud-skill-auditRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Real Skill packageSource verifiedClawHub registryAutomatic security hold
huawei-cloud-skill-audit
Audit Huawei Cloud skills for quality, security, and compliance using a three-check pipeline: skillspector (AI security) and gitleaks (credential leak). Generates structured reports with issue details and fix strategies. Triggers include: "审计技能","技能审计","检查技能质量","扫描技能问题","技能安全审计", "audit skill","check skill quality","scan skills for issues","skill audit", "华为云技能审计","技能合规检查","skill gate","质量门禁","技能检查", "audit huawei cloud skill","verify skill compliance","技能质量检查","跑审计","安全扫描".
Identity and source
Publisher attributiondev-skillsregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 63% rule confidence
Package forminstruction with code28 recorded files
Canonical sourceClawHub registryclawhub:dev-skills-operator:huawei-cloud-skill-audit
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.
OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 9/20/2026.agents/skills/huawei-cloud-skill-auditRuntime, 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 · 9/20/2026skills/huawei-cloud-skill-auditRuntime, 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 signalcriticalDestructive command targets a system rootscripts/checks/runtime_security_rules.json:320 · confidence 98% highRemote content is piped directly to a shellscripts/skill_audit.py:187 · confidence 98% highRemote content is piped directly to a shellscripts/checks/runtime_security_rules.json:549 · confidence 98% highDynamic code or shell execution is presentSKILL.md:207 · confidence 78% highDynamic code or shell execution is presentreferences/security-audit-guide.md:25 · confidence 78% highDynamic code or shell execution is presentscripts/checks/runtime_security_rules.json:188 · confidence 78% highEncoded content is decoded and executedscripts/checks/runtime_security_rules.json:152 · confidence 90% mediumWorld-writable permissions are requestedscripts/checks/runtime_security_rules.json:341 · confidence 95% Open human review queue →
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
- 28 / 28 inspected as text
- Checked
- 9/20/2026, 4:09:55 PM
- Scanner
- 0.1.3
- Policy
- 1.0.3
8 automated findings
rm -rf /curl|shwget|basheval(eval(exec(base64chmod 7777 High/Critical review queue entries
STATIC_DESTRUCTIVE_ROOT_COMMANDpending
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_OBFUSCATED_EXECUTIONpending
7 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
- external write action — automatically inferred
9 dependency and API indicators
- api: clawhub.ai
- api: gh-proxy.com
- api: gh.ddlc.top
- api: gitcode.com
- api: github.com
- api: gitleaks.io
- api: obs-skills-repository.obs.cn-north-4.myhuaweicloud.com
- api: skillsapi.developer.myhuaweicloud.com
- api: support.huaweicloud.com
External clawhub result: suspicious
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
- 9/20/2026, 7:46:15 AM
- Release binding
- Matches this record
- skillspector: suspicious
- llm: suspicious
Recorded files
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
Package content hash
sha256:79b5cbb36435e55ad15d6060270e36437bfd1595f2e3c2ac6f81b0572541af04Show up to 28 recorded paths
references/acceptance-criteria.mdreferences/cli-installation-guide.mdreferences/gitcode-security-scanner.mdreferences/iam-policies.mdreferences/security-audit-guide.mdreferences/verification-method.mdscripts/check_protocol.pyscripts/check_registry.pyscripts/checks/__init__.pyscripts/checks/gitleaks_builtin_check.pyscripts/checks/gitleaks_check.pyscripts/checks/gitleaks_rules.jsonscripts/checks/hwcloud_spec_check.pyscripts/checks/markdownlint_check.pyscripts/checks/runtime_security_check.pyscripts/checks/runtime_security_rules.jsonscripts/checks/skill_quality_rules.jsonscripts/checks/skillcheck_check.pyscripts/checks/skillspector_builtin_check.pyscripts/checks/skillspector_check.pyscripts/checks/skillspector_rules.jsonscripts/ensure_cli.shscripts/hcloud-run.shscripts/install_cli.shscripts/skill_audit.pyskill-card.mdSKILL.mdskillcheck.toml
Source changelog
**Expanded to a three-check security pipeline with new runtime detection.** - Added a third check: runtime_security (36 CWE-based runtime patterns + 3 skill-quality rules). - Upgraded skillspector to 51 rules / 609 patterns (was 47/439). - Updated gitleaks integration to 42 rules (was 222, now high-confidence only). - Workflow now always executes all 39 runtime_security rules, regardless of scan level. - Documentation and command options updated to reflect stricter AST and severity handling. - Telemetry opt-out changed from `SKILL_QUALITY_REPORT=0` to `SKILL_QUALITY_DISABLE=1`.