Real Skill packageSource verifiedClawHub registry

skill-analysis

装 Skill 前，先过一遍安检 —— 纯本地 · 零外联 · 零第三方依赖，代码不出你的机器。①【一句话结论】BLOCK / NEED_REVIEW / PASS 准入判定 + 0-100 风险评分 + A-F 等级与发布建议。②【全自动守护】会话启动自动扫描、新装 Skill 静默体检。③【深度对抗】多层混淆解码、污点数据流、Unicode 走私指令解码、反序列化 RCE、沙箱动态取证。④【情报驱动】勒索病毒、提示注入、MCP 工具投毒、供应链投毒、金融欺诈诱导、身份自改写持久化。⑤【工程化】跨平台批量扫描、CI 门禁、SARIF/SBOM/JSON 导出。⑥【可自证可信】无自动更新、发布

Identity and source

Publisher attributionJiXiang-ccregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 66% rule confidence
Package forminstruction with code57 recorded files
Canonical sourceClawHub registryclawhub:jixiang-cc:skill-analysis
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 · 9/30/2026.claude/skills/skill-analysis

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 · 9/30/2026.agents/skills/skill-analysis

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 · 9/30/2026skills/skill-analysis

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 @jixiang-cc/skill-analysis
clawhub inspect @jixiang-cc/skill-analysis --version 3.3.6

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
partial text content
Files
40 / 57 inspected as text
Checked
9/30/2026, 5:29:52 AM
Scanner
0.1.3
Policy
1.0.3
7 automated findings
highRemote content is piped directly to a shellCHANGELOG.md:24 · confidence 98%curl|bash
highRemote content is piped directly to a shellreferences/troubleshooting.md:179 · confidence 98%curl | bash
highRemote content is piped directly to a shellrules/agent-config-poison.json:41 · confidence 98%wget|bash
highRemote content is piped directly to a shellrules/install-hooks.json:42 · confidence 98%wget\\b|bash
highRemote content is piped directly to a shellrules/mcp-dangers.json:15 · confidence 98%curl|bash
highDynamic code or shell execution is presentCHANGELOG.md:219 · confidence 78%eval(
highEncoded content is decoded and executedCHANGELOG.md:183 · confidence 90%base64
7 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_DYNAMIC_CODE_EXECUTIONpending
STATIC_OBFUSCATED_EXECUTIONpending
Open human review queue →
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
4 dependency and API indicators
  • api: 91.92.242.30
  • api: evil
  • api: skillhub.cn
  • api: snyk.io
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
9/30/2026, 3:44:09 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 hashsha256:23a505effa11a824c1fa103820a4236796a2bb690d592f6d76a4b7b6be1e7cb0
Show up to 30 recorded paths
  • _meta.json
  • CHANGELOG.md
  • ci_templates/github-action.yml
  • ci_templates/gitlab-ci.yml
  • config/policy.json
  • config/trust.json
  • openclaw-skill.json
  • publisher-signature.json
  • references/build.md
  • references/examples.md
  • references/limitations.md
  • references/risk-patterns.md
  • references/rules-authoring.md
  • references/threat-landscape-2026.md
  • references/troubleshooting.md
  • rules/agent-config-poison.json
  • rules/capability.json
  • rules/engine_hashes.json
  • rules/examples/ioc-examples.json
  • rules/exfil-combos.json
  • rules/fs-abuse.json
  • rules/install-hooks.json
  • rules/ioc.json
  • rules/malicious-hashes.json
  • rules/malware.json
  • rules/manifest.json
  • rules/mcp-dangers.json
  • rules/memory-poison.json
  • rules/module-shadowing.json
  • rules/network.json

Source changelog

**v3.3.6 平台兼容扩展与情报规则升级** - 新增对 17 类平台/Agent/IDE 的兼容分析 - 更新 2026H2 情报检测规则，包括 Gatekeeper 隔离属性类、SVG XSS、语义蠕虫 NL、凭证路径外传、生命周期脚本链等五大类