合规安检 Skill(锦衣卫)
SkillFiles & storageYour AI can screen incoming files and URLs against blacklists and policy rules, returning a clear pass or reject verdict for each one. This skill makes that check a mandatory first step, so nothing questionable moves forward in a document pipeline. Every scan also produces a detailed compliance report showing what was found and why the verdict was given.
Available today. Use it from your connected AI after setup.
No other account needed.
After adding it, ask your AI to scan any file or URL before it handles the content. In document workflows, make the scan a required first step so every item gets a verdict before moving on.
Then ask your AI: use the 合规安检 Skill(锦衣卫) skill
What your AI can do with it
- Screen incoming files against blacklists before they are processed
- Check external URLs against policy rules before they are used
- Return a clear pass or reject verdict for every scan
- Generate a detailed compliance report explaining each verdict
- Act as a required first step in document processing pipelines
What this skill tells your AI
The instructions your AI receives, as published by anbeime/skill in skills/antinet-security-scan/SKILL.md and read by ahel’s review.
使用方式
- 由锦衣卫 Worker 在收到文件/URL 时调用,作为流水线的第一道闸门。
- 输出结构化判定(
pass/reject),并写入 provenance 交由太史阁留痕。
输入(Input)
target:待检对象,二选一- 本地文件路径(PDF / PPT / Excel / Word / 图片)
- 外部 URL(需先解析域名)
policy_ref:(可选)覆盖默认策略的合规规则集引用
输出(Output)
verdict:pass或rejectreport:安全扫描报告,含命中的黑名单项、许可状态、风险等级trace_id:本次扫描的 provenance 追踪 ID(用于太史阁留痕)
依赖(Dependencies)
- Sci-Hub 等已知违规域名黑名单(本地 CSV/JSON)
- OA 文档许可校验库(本地规则)
- 文件类型探测(
python-magic)
失败处理(Failure Handling)
- 扫描服务不可用:拒绝文件并告警,绝不降级放行(零信任底线)。
- 文件类型无法识别:标记
reject并写入原因,交由管理员确认。 - 黑名单库读取失败:回退到「全拒 + 告警」保守策略,并提示运维修复。
复用价值(Reuse Value)
- 与具体业务解耦:任何文档处理系统(RAG、知识库、合同审查)均可直接挂载此 Skill 作入口安检。
- 判定标准可配置:通过替换
policy_ref适配不同行业的合规基线。
复赛代码包执行(runnable package)
- 真实入口:
scripts/run_security_scan.py - 执行等价于
core.runtime.AgentSession.run_stage("security-scan"),调用security.jinyiwei.JinYiWeiAgent(纯 Python,零外部依赖,可离线运行)。 - 运行:
python skills/security-scan/scripts/run_security_scan.py - 产物:
examples/snse_survey/skill_outputs/security_scan.json(黄卡 + 扫描报告)。
Signals
- GitHub stars
- 7k
- Forks
- 628
- Last commit
- Sep 2026
Others that do the same job
Advanced
- Catalog kind
- skill
- Gateway key
antinet-security-scan- Source
- github.com/anbeime/skill