AI-Infra-Guard is an AI security red-teaming platform that scans agents, skills, MCP servers, and AI infrastructure and evaluates LLM jailbreak resistance. It is used to identify security risks and vulnerabilities in AI systems. Catalogue add-ons support its scanning and evaluation workflows.
Borrowing it
Nothing to install: this file belongs to Tencent/AI-Infra-Guard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Tencent/AI-Infra-Guard/main/CLAUDE.mdgit clone --depth 1 https://github.com/Tencent/AI-Infra-GuardWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/tencent/ai-infra-guard/claude-md)<a href="https://agentmods.dev/instructions/tencent/ai-infra-guard/claude-md"><img src="https://agentmods.dev/badge/instructions/tencent/ai-infra-guard/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/tencent/ai-infra-guard/claude-md"><img src="https://agentmods.dev/badge/instructions/tencent/ai-infra-guard/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01179 | $0.01179 |
| Opus 5 | $0.00589 | $0.00589 |
| Sonnet 5 | $0.00236 | $0.00236 |
| Haiku 4.5 | $0.00118 | $0.00118 |
Grade A, and why
AI-Infra-Guard CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
AI-Infra-Guard (A.I.G) is an AI Red Teaming Platform by Tencent Zhuque Lab. It scans AI infrastructure for fingerprints, CVE vulnerabilities, MCP server risks, agent workflow issues, and jailbreak susceptibility. It uses a distributed server-agent architecture combining Go (backend/scanning engine) and Python (ML/LLM sub-projects).
Build Commands
# Build web server binary
CGO_ENABLED=0 go build -ldflags="-s -w" -trimpath -buildvcs=false -o ai-infra-guard ./cmd/cli/main.go
# Build agent binary
CGO_ENABLED=0 go build -ldflags="-s -w" -trimpath -buildvcs=false -o agent ./cmd/agent
# Validate YAML rules (run before committing rule changes)
go run cmd/yamlcheck/main.go
Test Commands
go test ./...
go test ./common/runner/...
go test ./common/fingerprints/parser/...
go test ./pkg/vulstruct/...
go test ./internal/mcp/...
Running the Application
# Docker (recommended)
docker-compose up -d
# From source: start web server
./ai-infra-guard webserver --server 127.0.0.1:8088
# CLI scan (no server required)
./ai-infra-guard scan -t http://target:port --fps data/fingerprints --vul data/vuln
# Agent (connects to a running server)
AIG_SERVER=localhost:8088 ./agent
Architecture
Distributed Server-Agent Model
Frontend (SPA, embedded) → REST API / SSE
→ WebSocket (/api/v1/agents/ws) → Agent Workers
- Webserver (
cmd/cli/main.go, port 8088): Gin HTTP server, task manager, SQLite persistence, SSE for live progress - Agent (
cmd/agent/main.go): Connects to server via WebSocket, executes tasks, streams results back
Four Task Types
| Task | Go Handler | Execution |
|---|---|---|
AI-Infra-Scan |
AIInfraScanAgent |
Pure Go fingerprint + CVE scan |
Mcp-Scan |
McpTask |
Spawns python mcp-scan/main.py |
Model-Redteam-Report |
PromptTask |
Spawns uv run AIG-PromptSecurity/cli_run.py |
Agent-Scan |
AgentTask |
Spawns python agent-scan/main.py |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 115 lines · 1,179 tokens per session scan A 9223c56a5f72
AI-Infra-Guard CLAUDE.md is an instructions file published in the GitHub repository Tencent/AI-Infra-Guard (6,199 stars, last pushed today), licensed Apache-2.0. It adds 1,179 tokens to every session, about $0.0059 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.