tencent/ai-infra-guard
13 skills
$npx skills add tencent/ai-infra-guardSkillInstalls
aig-agent-redteam当用户要求 AI/Agent 安全评估、蓝军演习、AI 安全审查、提示词注入测试、MCP/Skill/插件/代码包审计、Agent 工具链滥用测试，或需要生成类似渗透测试报告的 Markdown/HTML 时，必须使用本 skill。本 skill 让 Agent 以授权蓝军视角成为 AI 安全专家，面向 AI 产品、Agent、MCP Server、Skill、代码仓库和 AI 基础设施进行安全aig-scannerA.I.G Scanner — AI security scanning for infrastructure, AI tools / skills, AI Agents, and LLM jailbreak evaluation via Tencent Zhuque Lab AI-Infra-Guard. Uses built-in exec + Python script, no pluginauthorization-bypass-detectionDetect privilege escalation and unauthorized access via dialogue. Use when the agent has roles, admin functions, or multi-user data.data-leakage-detectionDetect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.direct-injection-detectionDetect direct prompt injection or instruction override via user message (no external content). Focuses on system/role override attempts.edgeone-clawscan--- name: edgeone-clawscan version: 1.0.15 author: aigsec/Tencent Zhuque Lab license: MIT description: > The first security skill to install after setting up OpenClaw — powered by Tencent Zhuque Ledgeone-skill-scannerScan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your devifile-path-traversal-detectionDetect unsafe file handling and path traversal in upload/save/extract flows. Focuses on user-controlled paths or filenames, not data leakage.hardcoded-secret-detectionDetect hardcoded secrets in code or configuration accessible to the target agent. Focuses on secrets embedded in source, configs, or IaC, not runtime leaks.indirect-injection-detectionDetect indirect prompt injection (goal hijack). Instructions hidden in "external" content (documents, RAG, web) that the agent processes. Use when the agent has document/RAG/web/file input.memory-poisoning-detectionDetect persistent instruction injection or long-term memory poisoning. Focus on writing/retaining hostile instructions for future tasks, not data leakage.owasp-asiOWASP Top 10 for Agentic Applications 2026 (ASI) classification framework. Use for mapping security findings to standardized risk categories.tool-abuse-detectionDetect tool misuse and unexpected code execution via dialogue testing. Use when the agent exposes file, code-execution, or network tools.