Real Skill packageSource verifiedClawHub registry

code-risk-agent

当用户需要扫描代码安全漏洞、审计代码、分析 C/Python 风险、检查依赖漏洞、或生成安全报告时触发。支持云端 LLM 语义分析和本地 GPU 回退。

Identity and source

Publisher attributionYANG WEI KEregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 63% rule confidence
Package forminstruction with code24 recorded files
Canonical sourceClawHub registryclawhub:a9320:code-risk-agent
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 · 8/15/2026.claude/skills/code-risk-agent

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 · 8/15/2026.agents/skills/code-risk-agent

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 · 8/15/2026skills/code-risk-agent

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 @a9320/code-risk-agent
clawhub inspect @a9320/code-risk-agent --version 0.1.0

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
21 / 23 inspected as text
Checked
8/15/2026, 7:03:12 AM
Scanner
0.1.3
Policy
1.0.3
2 automated findings
highDynamic code or shell execution is presentagents/static_analyzer.py:117 · confidence 78%eval(
highDynamic code or shell execution is presentcore/taint_analyzer.py:13 · confidence 78%eval(
2 High/Critical review queue entries
STATIC_DYNAMIC_CODE_EXECUTIONpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
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
16 dependency and API indicators
  • pypi: mcp >=1.0.0
  • pypi: httpx >=0.25
  • pypi: pydantic >=2.0
  • pypi: rich >=13.0
  • pypi: semgrep >=1.0
  • pypi: pyyaml >=6.0
  • pypi: starlette >=0.27
  • pypi: uvicorn >=0.24
  • api: api.anthropic.com
  • api: api.deepseek.com
  • api: api.openai.com
  • api: cwe.mitre.org
  • api: github.com
  • api: nvd.nist.gov
  • api: owasp.org
  • api: raw.githubusercontent.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
8/15/2026, 7:11:33 AM
Release binding
Matches this record
  • vt: clean
  • 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:b0a169c94d38776235bb83234efe27b6f407672206dc86523d4215e7f4108f95
Show up to 24 recorded paths
  • _meta.json
  • agents/__init__.py
  • agents/deep_verifier.py
  • agents/report_generator.py
  • agents/semantic_analyzer.py
  • agents/static_analyzer.py
  • assets/icon.png
  • assets/promo_banner.png
  • core/__init__.py
  • core/attack_knowledge.py
  • core/cve_client.py
  • core/dependency_scanner.py
  • core/llm_client.py
  • core/memory.py
  • core/models.py
  • core/retry.py
  • core/semgrep_runner.py
  • core/taint_analyzer.py
  • mcp-server/requirements.txt
  • mcp-server/server.py
  • package.json
  • README_CN.md
  • skill-card.md
  • SKILL.md

Source changelog

Initial release with advanced code security auditing and vulnerability scanning for C and Python: - Scans code for vulnerabilities, audits projects, analyzes risk, checks dependencies, and generates security reports. - Supports both semantic cloud LLM analysis and local GPU fallback. - Exposes two tools: code scan and CVE lookup. - Returns structured JSON reports with clear Markdown rendering guidelines for results and recommendations. - Automatic fallback to pure static analysis if cloud LLM/semgrep unavailable. - Strict privacy controls and downgrade strategies for environments lacking cloud or database support.