agentrigs
+ submit rig
~ / rigs / Tencent / AI-Infra-Guard

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.

↗ GitHub ★ 6,725 apache-2.0 updated 6d ago project Claude CodeCodex
share on X
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
CONTEXT TAX · EVERY TURN
~1.9k tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit Tencent/AI-Infra-Guard/skills ./rig-ai-infra-guard/skills

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit Tencent/AI-Infra-Guard/agent-scan/agent_scan/prompt/skills/agentic-supply-chain-detection .claude/skills/agentic-supply-chain-detection
$ npx degit Tencent/AI-Infra-Guard/agent-scan/agent_scan/prompt/skills/authorization-bypass-detection .claude/skills/authorization-bypass-detection
$ npx degit Tencent/AI-Infra-Guard/agent-scan/agent_scan/prompt/skills/cascading-failure-detection .claude/skills/cascading-failure-detection
$ npx degit Tencent/AI-Infra-Guard/agent-scan/agent_scan/prompt/skills/data-leakage-detection .claude/skills/data-leakage-detection
$ npx degit Tencent/AI-Infra-Guard/agent-scan/agent_scan/prompt/skills/direct-injection-detection .claude/skills/direct-injection-detection
$ npx degit Tencent/AI-Infra-Guard/agent-scan/agent_scan/prompt/skills/file-path-traversal-detection .claude/skills/file-path-traversal-detection
$ npx degit Tencent/AI-Infra-Guard/agent-scan/agent_scan/prompt/skills/hardcoded-secret-detection .claude/skills/hardcoded-secret-detection
$ npx degit Tencent/AI-Infra-Guard/agent-scan/agent_scan/prompt/skills/human-agent-trust-exploit-detection .claude/skills/human-agent-trust-exploit-detection
$ npx degit Tencent/AI-Infra-Guard/agent-scan/agent_scan/prompt/skills/indirect-injection-detection .claude/skills/indirect-injection-detection
$ npx degit Tencent/AI-Infra-Guard/agent-scan/agent_scan/prompt/skills/inter-agent-comm-security-detection .claude/skills/inter-agent-comm-security-detection
$ npx degit Tencent/AI-Infra-Guard/agent-scan/agent_scan/prompt/skills/memory-poisoning-detection .claude/skills/memory-poisoning-detection
$ npx degit Tencent/AI-Infra-Guard/agent-scan/agent_scan/prompt/skills/owasp-asi .claude/skills/owasp-asi
$ npx degit Tencent/AI-Infra-Guard/agent-scan/agent_scan/prompt/skills/tool-abuse-detection .claude/skills/tool-abuse-detection
$ npx degit Tencent/AI-Infra-Guard/agent-scan/agent_scan/prompt/skills/unexpected-code-execution-detection .claude/skills/unexpected-code-execution-detection
$ npx degit Tencent/AI-Infra-Guard/agent-scan/agent_scan/prompt/skills/web-exfiltration-detection .claude/skills/web-exfiltration-detection
$ npx degit Tencent/AI-Infra-Guard/skills/aig-agent-redteam .claude/skills/aig-agent-redteam
$ npx degit Tencent/AI-Infra-Guard/skills/aig-scanner .claude/skills/aig-scanner
$ npx degit Tencent/AI-Infra-Guard/skills/edgeone-clawscan .claude/skills/edgeone-clawscan
$ npx degit Tencent/AI-Infra-Guard/skills/edgeone-skill-scanner .claude/skills/edgeone-skill-scanner

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(.env)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(~/.aws/**)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/*.key)",
      "Read(**/.env.*)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(git rebase *)",
      "Bash(wget *)",
      "Bash(npm publish:*)",
      "Bash(git commit *)",
      "Bash(gh pr merge *)"
    ]
  }
}

Skills (19)

agentic-supply-chain-detectionauthorization-bypass-detectioncascading-failure-detectiondata-leakage-detectiondirect-injection-detectionfile-path-traversal-detectionhardcoded-secret-detectionhuman-agent-trust-exploit-detectionindirect-injection-detectioninter-agent-comm-security-detectionmemory-poisoning-detectionowasp-asitool-abuse-detectionunexpected-code-execution-detectionweb-exfiltration-detectionaig-agent-redteamaig-scanneredgeone-clawscanedgeone skill scanner

Similar rigs

obra/superpowers
An agentic skills framework & software development methodology that works.
★ 294k project CodexGemini CLI 15 skills 12d ago
Skill Collector 3.0k tok ·
anthropics/skills
Public repository for Agent Skills
★ 180k collection Claude Code 19 skills 4d ago
Skill Collector 1.3k tok ·
anthropics/claude-code
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
★ 149k project Claude Code 10 skills 6d ago
Skill Collector 1.4k tok ·
JuliusBrussee/caveman
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
★ 110k project Claude CodeCodexGemini CLI 22 skills 3 agents 1d ago
Skill Collector 16.5k tok ·
copied ✓