Updated 2d ago
by 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.
7.4k GitHub stars (7,380)
+626 in 30 days
| Period | New stars |
|---|---|
| Sep 27–28 (2 days) | +10 |
| Sep 29 | +22 |
| Sep 30 | +22 |
| Oct 1 | +2 |
| Oct 2 | +16 |
| Oct 3 | +41 |
| Oct 4 | +21 |
| Oct 5 | +19 |
| Oct 6 | +7 |
| Oct 7 | +12 |
| Oct 8 | +7 |
| Oct 9 | +18 |
| Oct 10 | +13 |
| Oct 11 | +17 |
| Oct 12 | +5 |
| Oct 13 | +11 |
| Oct 14 | +18 |
| Oct 15 | +14 |
| Oct 16 | +14 |
| Oct 17 | +10 |
| Oct 18 | 0 |
| Oct 19 | +15 |
| Oct 20 | +8 |
| Oct 21 | +13 |
| Oct 22 | +3 |
| Oct 23 | +7 |
| Oct 24 | +105 |
| Oct 25 | +38 |
| Oct 26 | +8 |
| Oct 27 | +26 |
| Oct 28 | +31 |
| Oct 29 | +36 |
| Oct 30 | +44 |
| Oct 31 | +7 |
| Nov 1 | +15 |
| Nov 2 | +37 |
| Nov 3 | +56 |
| Nov 4 | +27 |
| Nov 5 | +11 |
- 20 skills (20 skills found in its SKILL.md files)
- 735 forks (735 forks)
- 2d ago last update (Last updated 2d ago)
Install
Skills CLI
npx skills add Tencent/AI-Infra-Guard
Asks which skills and agents to install. Just one: npx skills add Tencent/AI-Infra-Guard --skill aig-agent-redteam — add -g for every project.
Claude Code
git clone https://github.com/Tencent/AI-Infra-Guardcp -r "AI-Infra-Guard/skills/aig-agent-redteam" ~/.claude/skills/
Copies the aig-agent-redteam skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add Tencent/AI-Infra-Guard
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
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。
skills/aig-agent-redteam/ on GitHub (opens in a new tab)SKILL.md -
edgeone-clawscan
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 c…
skills/edgeone-clawscan/ on GitHub (opens in a new tab)SKILL.md -
edgeone skill scanner
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…
skills/edgeone-skill-scanner/ on GitHub (opens in a new tab)SKILL.md -
pdf-summarizer
Summarize the key points of a PDF document into a short bullet list.
Research/pikit/ on GitHub (opens in a new tab)pikit/ carriers/ SKILL.md -
agentic-supply-chain-detection
Detect agentic supply-chain risks: compromised dependencies, malicious plugins/tools/models, and untrusted update sources.
agent-scan/agent_scan/ on GitHub (opens in a new tab)prompt/ skills/ agentic-supply-chain-detection/ SKILL.md -
authorization-bypass-detection
Detect privilege escalation and unauthorized access via dialogue. Use when the agent has roles, admin functions, or multi-user data.
agent-scan/agent_scan/ on GitHub (opens in a new tab)prompt/ skills/ authorization-bypass-detection/ SKILL.md -
cascading-failure-detection
Detect error propagation, chain failures, and single-point breakdowns that cascade across agent workflows.
agent-scan/agent_scan/ on GitHub (opens in a new tab)prompt/ skills/ cascading-failure-detection/ SKILL.md -
data-leakage-detection
Detect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.
agent-scan/agent_scan/ on GitHub (opens in a new tab)prompt/ skills/ data-leakage-detection/ SKILL.md -
direct-injection-detection
Detect direct prompt injection or instruction override via user message (no external content). Focuses on system/role override attempts.
agent-scan/agent_scan/ on GitHub (opens in a new tab)prompt/ skills/ direct-injection-detection/ SKILL.md -
file-path-traversal-detection
Detect unsafe file handling and path traversal in upload/save/extract flows. Focuses on user-controlled paths or filenames, not data leakage.
agent-scan/agent_scan/ on GitHub (opens in a new tab)prompt/ skills/ file-path-traversal-detection/ SKILL.md -
hardcoded-secret-detection
Detect hardcoded secrets in code or configuration accessible to the target agent. Focuses on secrets embedded in source, configs, or IaC, not runtime leaks.
agent-scan/agent_scan/ on GitHub (opens in a new tab)prompt/ skills/ hardcoded-secret-detection/ SKILL.md -
human-agent-trust-exploit-detection
Detect social engineering, deceptive responses, false assurances, or prompts that induce unsafe user actions.
agent-scan/agent_scan/ on GitHub (opens in a new tab)prompt/ skills/ human-agent-trust-exploit-detection/ SKILL.md -
indirect-injection-detection
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.
agent-scan/agent_scan/ on GitHub (opens in a new tab)prompt/ skills/ indirect-injection-detection/ SKILL.md -
inter-agent-comm-security-detection
Detect data leakage, missing boundaries, or privilege mismatch in inter-agent communication.
agent-scan/agent_scan/ on GitHub (opens in a new tab)prompt/ skills/ inter-agent-comm-security-detection/ SKILL.md -
memory-poisoning-detection
Detect persistent instruction injection or long-term memory poisoning. Focus on writing/retaining hostile instructions for future tasks, not data leakage.
agent-scan/agent_scan/ on GitHub (opens in a new tab)prompt/ skills/ memory-poisoning-detection/ SKILL.md -
memory-rag-poisoning-detection
Detect persistent-memory poisoning and RAG/knowledge-base contamination via dialogue testing. Use when the agent has long-term memory, a user/preference store, or writes to a retrievable knowledge base.
agent-scan/agent_scan/ on GitHub (opens in a new tab)prompt/ skills/ memory-rag-poisoning-detection/ SKILL.md -
owasp-asi
OWASP Top 10 for Agentic Applications 2026 (ASI) classification framework. Use for mapping security findings to standardized risk categories.
agent-scan/agent_scan/ on GitHub (opens in a new tab)prompt/ skills/ owasp-asi/ SKILL.md -
tool-abuse-detection
Detect tool misuse and unexpected code execution via dialogue testing. Use when the agent exposes file, code-execution, or network tools.
agent-scan/agent_scan/ on GitHub (opens in a new tab)prompt/ skills/ tool-abuse-detection/ SKILL.md -
unexpected-code-execution-detection
Detect command injection, eval/exec usage, remote execution, or arbitrary code loading.
agent-scan/agent_scan/ on GitHub (opens in a new tab)prompt/ skills/ unexpected-code-execution-detection/ SKILL.md -
web-exfiltration-detection
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.
agent-scan/agent_scan/ on GitHub (opens in a new tab)prompt/ skills/ web-exfiltration-detection/ SKILL.md
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.