Index of every page on this site: llms.txt
All skills
tencent avatar

Tencent/AI-Infra-Guard

A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.

main Updated 2 days agoGitHub
README badge for tencent/ai-infra-guard

Repository statistics

  • Indexed skills

    18

  • Skill groups

    1

  • GitHub stars

    7,578

  • Forks

    775

18 total

OWASP Top 10 for Agentic Applications 2026 (ASI) classification framework. Use for mapping security findings to standardized risk categories.

Updated

Detect agentic supply-chain risks: compromised dependencies, malicious plugins/tools/models, and untrusted update sources.

Updated

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 指纹识别、证据聚合、报告渲染等确定性辅助任务。

Updated

Detect error propagation, chain failures, and single-point breakdowns that cascade across agent workflows.

Updated

Detect social engineering, deceptive responses, false assurances, or prompts that induce unsafe user actions.

Updated

Detect data leakage, missing boundaries, or privilege mismatch in inter-agent communication.

Updated

Detect command injection, eval/exec usage, remote execution, or arbitrary code loading.

Updated

Detect privilege escalation and unauthorized access via dialogue. Use when the agent has roles, admin functions, or multi-user data.

Updated

Detect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.

Updated

Detect direct prompt injection or instruction override via user message (no external content). Focuses on system/role override attempts.

Updated

Detect unsafe file handling and path traversal in upload/save/extract flows. Focuses on user-controlled paths or filenames, not data leakage.

Updated

Detect hardcoded secrets in code or configuration accessible to the target agent. Focuses on secrets embedded in source, configs, or IaC, not runtime leaks.

Updated

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.

Updated

Detect persistent instruction injection or long-term memory poisoning. Focus on writing/retaining hostile instructions for future tasks, not data leakage.

Updated

Detect tool misuse and unexpected code execution via dialogue testing. Use when the agent exposes file, code-execution, or network tools.

Updated

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 or personal context.

Updated

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 prevent data leaks and privacy risks. Backed by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). Use when the user asks to start a security health check or security scan for the current OpenClaw environment, such as `开始安全体检`, `做一次安全体检`, `开始安全扫描`, `全面安全检查`, or `检查 OpenClaw 安全`; also use when the user asks to audit a specific skill before installation, review installed skills for supply chain risk, or investigate whether a skill is safe. Do not trigger for general OpenClaw usage, project debugging, environment setup, or normal development requests. Optional cloud mode: set AIG_CLOUD_LOOKUP=off for zero outbound HTTPS; when enabled, only skill_name, source label, and OpenClaw version are sent to A.I.G (never skill bodies, chats, or workspace files).

Updated

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 Code, OpenClaw and more. Triggers on: `这个 skill 安全吗`, `skill 安全扫描`, `检查 skill 安全`, `audit skill`, `scan skill`, `check skill safety`, `analyze skill`, `inspect skill`, `verify skill`, `skill security`, `skill supply chain`. Do NOT trigger for general agent usage, full system health checks, project debugging, or normal development.

Updated

The badge links readers to this page. It shows the skilld mark and no counts, and it follows the reader's light or dark GitHub theme.

<a href="https://skilld.dev/gh/tencent/ai-infra-guard"> <picture> <source media="(prefers-color-scheme: dark)" srcset="https://skilld.dev/b/tencent/ai-infra-guard?theme=dark"> <source media="(prefers-color-scheme: light)" srcset="https://skilld.dev/b/tencent/ai-infra-guard?theme=light"> <img alt="Skill repository on skilld.dev" src="https://skilld.dev/b/tencent/ai-infra-guard?theme=light"> </picture> </a>