Menu
O SkillsMP coletou 19 skills de Tencent/AI-Infra-Guard. Abra uma skill para revisar a origem e os detalhes.
Mostrando 19 de 19 skills coletadas.
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 基础设施进行安全演习。优先使用第一性原理推理和真实证据，而不是机械跑 payload 库；脚本只用于 HTTP…
Idioma do texto original: chinês
Detect agentic supply-chain risks: compromised dependencies, malicious plugins/tools/models, and untrusted update sources.
Idioma do texto original: inglês
Detect error propagation, chain failures, and single-point breakdowns that cascade across agent workflows.
Idioma do texto original: inglês
Detect social engineering, deceptive responses, false assurances, or prompts that induce unsafe user actions.
Idioma do texto original: inglês
Detect data leakage, missing boundaries, or privilege mismatch in inter-agent communication.
Idioma do texto original: inglês
Detect command injection, eval/exec usage, remote execution, or arbitrary code loading.
Idioma do texto original: inglês
OWASP Top 10 for Agentic Applications 2026 (ASI) classification framework. Use for mapping security findings to standardized risk categories.
Idioma do texto original: inglês
Detect privilege escalation and unauthorized access via dialogue. Use when the agent has roles, admin functions, or multi-user data.
Idioma do texto original: inglês
Detect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.
Idioma do texto original: inglês
Detect direct prompt injection or instruction override via user message (no external content). Focuses on system/role override attempts.
Idioma do texto original: inglês
Detect unsafe file handling and path traversal in upload/save/extract flows. Focuses on user-controlled paths or filenames, not data leakage.
Idioma do texto original: inglês
Detect hardcoded secrets in code or configuration accessible to the target agent. Focuses on secrets embedded in source, configs, or IaC, not runtime leaks.
Idioma do texto original: inglês
Detect 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.
Idioma do texto original: inglês
Detect persistent instruction injection or long-term memory poisoning. Focus on writing/retaining hostile instructions for future tasks, not data leakage.
Idioma do texto original: inglês
Detect tool misuse and unexpected code execution via dialogue testing. Use when the agent exposes file, code-execution, or network tools.
Idioma do texto original: inglês
Detect data exfiltration via URL path encoding and chained web_fetch navigation. Covers fake trusted UI injection, letter-level URL path exfiltration, and multi-hop navigation hijacking. Use when the agent has web/URL fetch capability and stores user memory…
Idioma do texto original: inglês
A.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 plugin required. Requires AIG_BASE_URL to be configured. Triggers…
Idioma do texto original: inglês
The first security skill to install after setting up OpenClaw — powered by Tencent Zhuque Lab. Works like an antivirus for your AI environment: audits installed skills, scans skills before installation, and performs a full OpenClaw security health check to…
Idioma do texto original: Vários idiomas
Scan 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 device. Compatible with CodeBuddy, Cursor, Windsurf, Claude…
Idioma do texto original: inglês