security

Agent Skills › iii-experimental/agentos › security

security

GitHub

提供安全扫描能力，包括注入检测、权限检查及审计日志查询。通过调用本地API接口，辅助Agent识别安全风险并验证操作合规性，保障系统运行安全。

plugin/skills/security/SKILL.md iii-experimental/agentos

Trigger Scenarios

需要检测输入是否包含注入攻击风险需要验证Agent对特定资源的访问权限需要查询或审计Agent的安全操作记录

Install

npx skills add iii-experimental/agentos --skill security -g -y

More Options

Non-standard path

npx skills add https://github.com/iii-experimental/agentos/tree/main/plugin/skills/security -g -y

Use without installing

npx skills use iii-experimental/agentos@security

指定 Agent (Claude Code)

npx skills add iii-experimental/agentos --skill security -a claude-code -g -y

安装 repo 全部 skill

npx skills add iii-experimental/agentos --all -g -y

预览 repo 内 skill

npx skills add iii-experimental/agentos --list

SKILL.md

Frontmatter

{
    "name": "security",
    "effort": "normal",
    "toolScope": [
        "Bash",
        "Read"
    ],
    "description": "Security scanning — injection detection, capability checks, audit trails"
}

Security operations:

Scan injection: curl -X POST http://localhost:3111/api/security/scan -H 'Content-Type: application/json' -d '{"input": "<text>", "checks": ["injection", "traversal", "command"]}'
Check capability: curl -X POST http://localhost:3111/api/security/capability -H 'Content-Type: application/json' -d '{"agentId": "claude-code", "action": "write", "resource": "/path"}'
Audit: curl http://localhost:3111/api/security/audit?agentId=claude-code&limit=50