- name
对进入系统的文件或 URL 执行安全与合规扫描,输出 pass/reject 判定与扫描报告,作为所有文档处理的强制前置关卡。
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add anbeime/skill --skill security-scan -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add anbeime/skill --skill security-scan -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add anbeime/skill --skill security-scan -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add anbeime/skill --skill security-scan -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/anbeime/skill/tree/HEAD/antinet-agentteams/skills/security-scanFrom the publisher
pass / reject),并写入 provenance 交由太史阁留痕。target:待检对象,二选一
policy_ref:(可选)覆盖默认策略的合规规则集引用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)python-magic)reject 并写入原因,交由管理员确认。policy_ref 适配不同行业的合规基线。scripts/run_security_scan.pycore.runtime.AgentSession.run_stage("security-scan"),调用 security.jinyiwei.JinYiWeiAgent(纯 Python,零外部依赖,可离线运行)。python skills/security-scan/scripts/run_security_scan.pyexamples/snse_survey/skill_outputs/security_scan.json(黄卡 + 扫描报告)。© 2026 Skills Rack.
---name: security-scandescription: 对进入系统的文件或 URL 执行安全与合规扫描,输出 pass/reject 判定与扫描报告,作为所有文档处理的强制前置关卡。---# antinet-agentteams/skills/security-scan/SKILL.mdFAQ
Download antinet-agentteams/skills/security-scan/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/anbeime/skill.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.