Real Skill packageSource verifiedClawHub registry

skill-security-checker

Skill Security — 安全审计扫描器，帮助你快速发现 Skill 中的安全风险。轻量 SAST 污点追踪（Python AST + JS 词法近似，source→sink 证据链降误报）、规则引擎（YAML 规则包热插拔扩展）、社区规则（schema 校验 + 来源记录 + 签名验证）、提示注入 ML 语义检测（ONNX + 正则降级）、系统级行为捕获（eBPF Linux / ETW Windows）、动态沙箱执行扫描、供应链风险分析、CVE 离线缓存、恶意 Skill 指纹库、健康度与合规检查（质量+结构+权限合并）、全局排除配置、CI/CD 集成、JSON/HTML/SARIF 报告生成。

Identity and source

Publisher attributionfyniujinregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 63% rule confidence
Package forminstruction with code31 recorded files
Canonical sourceClawHub registryclawhub:fyniujin:skill-security-checker
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 · 8/25/2026.claude/skills/skill-security-checker

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 · 8/25/2026.agents/skills/skill-security-checker

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 · 8/25/2026skills/skill-security-checker

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 @fyniujin/skill-security-checker
clawhub inspect @fyniujin/skill-security-checker --version 3.3.0

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
31 / 31 inspected as text
Checked
8/25/2026, 1:54:37 AM
Scanner
0.1.3
Policy
1.0.3
8 automated findings
highRemote content is piped directly to a shellscripts/rules/command_injection.yaml:8 · confidence 98%curl.*(sh|bash
highDynamic code or shell execution is presentSKILL.md:35 · confidence 78%eval(
highDynamic code or shell execution is presentscripts/taint_tracker.py:41 · confidence 78%eval(
highDynamic code or shell execution is presentreferences/scan-patterns.md:82 · confidence 78%eval(
highEncoded content is decoded and executedSKILL.md:505 · confidence 90%base64
highEncoded content is decoded and executedreferences/scan-patterns.md:59 · confidence 90%base64
mediumPrompt-override language requires reviewSKILL.md:192 · confidence 62%ignore previous instructions
mediumPrompt-override language requires reviewscripts/rules/prompt_injection.yaml:7 · confidence 62%ignore previous instructions
6 High/Critical review queue entries
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_OBFUSCATED_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
8 dependency and API indicators
  • api: api.github.com
  • api: api.osv.dev
  • api: clawhub.ai
  • api: github.com
  • api: pypi.org
  • api: raw.githubusercontent.com
  • api: registry.npmjs.org
  • api: services.nvd.nist.gov
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
8/24/2026, 4:26:15 PM
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 hashsha256:2c42012d273c6a29f010fd73a49f258875f933a509c916eff2ed862292efe6a6
Show up to 30 recorded paths
  • _meta.json
  • references/scan-patterns.md
  • scripts/audit.py
  • scripts/ci_templates/gitlab-ci.yml
  • scripts/ci_templates/skill-scan.yml
  • scripts/community_rules.py
  • scripts/global_exclude.py
  • scripts/malicious_db.py
  • scripts/rules_engine.py
  • scripts/rules/__init__.py
  • scripts/rules/command_injection.yaml
  • scripts/rules/credential_leak.yaml
  • scripts/rules/dangerous_functions.yaml
  • scripts/rules/path_traversal.yaml
  • scripts/rules/prompt_injection.yaml
  • scripts/rules/ssrf.yaml
  • scripts/sandbox/__init__.py
  • scripts/sandbox/backends/__init__.py
  • scripts/sandbox/backends/degraded.py
  • scripts/sandbox/backends/docker_backend.py
  • scripts/sandbox/backends/winsandbox_backend.py
  • scripts/sandbox/ml_detect.py
  • scripts/sandbox/monitor.py
  • scripts/sandbox/report.py
  • scripts/sandbox/rules.py
  • scripts/sandbox/runner.py
  • scripts/sandbox/system_monitor.py
  • scripts/supply_chain.py
  • scripts/taint_tracker.py
  • skill-card.md

Source changelog

skill-security-checker v3.3.0 - 新增轻量 SAST 污点追踪（Python AST/JS 词法级，source→sink 证据链，降误报）。 - 支持社区安全规则包（schema 校验、签名验证、来源记录），命令行可加 --community-rules。 - 健康度与合规检查全新合并，结构/质量/权限合规统一出口，报告结构更清晰。 - 新增 scripts/community_rules.py、scripts/taint_tracker.py，移除 skill-card.md。 - 规则引擎、行为捕获、ML检测及主功能保持兼容，常规参数和用法未变。

Release security diff

highCompared fixed releases 3.2.0 and 3.3.0; 1 finding and 1 permission indicators were added.

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

Permission escalation detected
Change reasons and limitations
  • new high finding
  • new sensitive permission
  • finding surface changed
  • permission 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.

3.2.08/17/2026sha256:8dd54ba4b68e077989450d13a409a1915448a55295217c7927c16e0b5ce93b3c