Real Skill packageSource verifiedClawHub registry

contract-review

对中文合同进行智能风险审查，识别条款风险、提取关键信息、生成审查报告，覆盖买卖/技术/租赁/劳动等常见合同类型。v5.0 新增法条引用溯源、合同谈判辅助、中英双语对照审查。v5.1 新增指导案例引用溯源、金额校验引擎、多语种扩展（日/韩）。

Identity and source

Publisher attributionfyniujinregistry owner unverified by skillvetai
Functional categoryEnterprise Functionsautomatically inferred · 58% rule confidence
Package forminstruction with code79 recorded files
Canonical sourceClawHub registryclawhub:fyniujin:contract-review
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 · 8/17/2026.claude/skills/contract-review

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 · 8/17/2026.agents/skills/contract-review

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 · 8/17/2026skills/contract-review

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/contract-review
clawhub inspect @fyniujin/contract-review --version 5.1.0

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
partial text content
Files
40 / 79 inspected as text
Checked
8/17/2026, 10:02:08 AM
Scanner
0.1.3
Policy
1.0.3
7 automated findings
highRemote content is piped directly to a shellSKILL.md:343 · confidence 98%curl -fsSL https://ollama.ai/install.sh | sh
highRemote content is piped directly to a shellscripts/main.py:126 · confidence 98%curl -fsSL https://ollama.ai/install.sh | sh
highRemote content is piped directly to a shellREADME.md:179 · confidence 98%curl -fsSL https://ollama.ai/install.sh | sh
highDynamic code or shell execution is presentscripts/amount_validator.py:442 · confidence 78%eval(
mediumRemote installer is downloaded without an integrity checkSKILL.md:343 · confidence 70%curl -fsSL https://ollama.ai/install.sh
mediumRemote installer is downloaded without an integrity checkscripts/main.py:126 · confidence 70%curl -fsSL https://ollama.ai/install.sh
mediumRemote installer is downloaded without an integrity checkREADME.md:179 · confidence 70%curl -fsSL https://ollama.ai/install.sh
4 High/Critical review queue entries
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
STATIC_DOWNLOAD_PIPE_TO_SHELLpending
STATIC_DYNAMIC_CODE_EXECUTIONpending
Open human review queue →
6 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
  • external write action — automatically inferred
12 dependency and API indicators
  • pypi: pdfplumber >=0.10.0
  • pypi: python-docx >=1.1.0
  • pypi: paddleocr >=2.7.0
  • pypi: opencv-python >=4.8.0
  • pypi: PyMuPDF >=1.23.0
  • pypi: openai >=1.0.0
  • pypi: pyyaml >=6.0
  • pypi: requests >=2.31.0
  • pypi: psutil >=5.9.0
  • api: api.openai.com
  • api: ollama.ai
  • 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
8/17/2026, 9:41:39 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 hashsha256:9b28dd12f137978ab8c4056c85e74ef05897058f5b2670ec74bd98114db9d472
Show up to 30 recorded paths
  • assets/report_template.md
  • pyproject.toml
  • README.md
  • references/bilingual_glossary.yaml
  • references/checklists/capital_increase.md
  • references/checklists/construction.md
  • references/checklists/equity_transfer.md
  • references/checklists/ip_license.md
  • references/checklists/labor_contract_deep.md
  • references/checklists/nda.md
  • references/checklists/procurement_framework.md
  • references/checklists/valuation_adjustment.md
  • references/clause_library/clause_index.yaml
  • references/clause_library/clauses.json
  • references/clause_library/versions.yaml
  • references/compliance_checklist.md
  • references/contract_types.yaml
  • references/contract_types/capital_increase.yaml
  • references/contract_types/construction.yaml
  • references/contract_types/equity_transfer.yaml
  • references/contract_types/ip_license.yaml
  • references/contract_types/labor_contract_deep.yaml
  • references/contract_types/nda.yaml
  • references/contract_types/procurement_framework.yaml
  • references/contract_types/valuation_adjustment.yaml
  • references/guiding_cases/cases.json
  • references/guiding_cases/index.json
  • references/guiding_cases/update_log.json
  • references/industries/construction/cases.md
  • references/industries/construction/rules.yaml

Source changelog

contract-review v5.1.0 introduces advanced case referencing, enhanced financial validation, and multilingual support: - Added citation tracing for Supreme People's Court guiding cases, enhancing the credibility of review conclusions. - Introduced a database of 30 guiding cases across 20 contract categories, with monthly update reminders. - Implemented a key amount verification engine for consistency between numbers and written forms and cross-checks (e.g. unit price × quantity = total), with error rate <0.5%. - Expanded multilingual review capability: now supports Chinese-Japanese and Chinese-Korean bilingual review, with 200+ legal term pairs added for each. - Included new Japanese and Korean legal terminology tables, covering major legal and business scenarios.