AI-Infra-Guard by Tencent Zhuque Lab

Offensive & Pentesting

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

Track releases GitHub Website

Python Latest v4.1.10 · 6d ago Security brief →

Features

Scans AI infrastructure components for vulnerabilities (e.g., OpenClaw, Agent Scan)
Evaluates prompt‑injection and jailbreak risks with dedicated security operators
Provides WebSocket agent provider support for real‑time scanning

Recent releases

View all 32 releases →

No immediate action

v4.1.10 Mixed 6d

CVE rules + WS agents + scan fixes

Open

Review required

v4.1.9 New feature 13d

Auth RBAC

Prompt security operators + scan defense

Open

No immediate action

v4.1.8 Bug fix 20d

Case‑insensitive tool name lookup

Open

v4.1.6 Bug fix 1mo

Notable features

Add git to Docker runtime dependencies
Replace zip download with git clone in Data Sync, removing github_token dependency
Support manual updates of jailbreak datasets, fingerprints, and vulnerability databases

Full changelog

[v4.1.6] - 2026-04-23

Added

Docker: Add git to runtime dependencies in Dockerfile (69f7430)
Vuln Rules: Add AIG vulnerability rules [2026-04-23] (#350)
Vuln Rules: Detect exposed AI agent config files (claude_desktop_config.json, mcp.json, etc.) (#340)
Vuln Rules: Add Trae IDE and CodeBuddy MCP config paths, extend .env key patterns
Data Sync: Replace zip download with git clone, remove github_token dependency (#327)
Manual Updates: Support manual updates to the latest jailbreak datasets, fingerprints, and vulnerability databases
Update API: Merge update-status into update-data endpoint

Fixed

Vuln Rules: Revert .env matcher to API key pattern matching
Vuln Rules: Remove mcpServers field dependency, match on file format only
Vuln Rules: Replace substring match with regex to reduce false positives
Update API: Return status=1 when last sync failed
Update API: Unify response format to {status, message, data}
Update API: Remove request params, always sync main branch
Data Sync: Harden update_api against CodeQL path-injection and command-injection alerts
Vuln Rules: Update GHSA-8fmp-37rc-p5g7.yaml and OpenClaw versioning rule

Contributors

Special thanks to @feiyang666, @zhuque, @boyhack, @aigsec, @aig-doc-bot

View release on GitHub

v4.1.4 New feature 1mo

Notable features

MCP Scan: multi‑turn red team attack module with TAP and Crescendo strategies
System API: data auto‑sync endpoints (`POST /api/v1/system/update-data`, `GET /api/v1/system/update-status`)
Agent Scan API: inline `agent_config` support, optional verify flag

Full changelog

[v4.1.4] - 2026-04-17

Security

TLS: Support HTTPS connections with self-signed/private CA certificates for model endpoints; add InsecureSkipVerify option (#306, closes #302)

Added

MCP Scan: Add multi-turn red team attack module with TAP and Crescendo strategies (#299)
System API: Add data auto-sync API (POST /api/v1/system/update-data, GET /api/v1/system/update-status) for syncing data/ directory (#301)
Agent Scan API: Support inline agent_config in agent scan API, make verify optional on save (#322)
CLI: Support --agent-config-file for inline YAML agent scan config (aig-scanner v1.0.3)
Security Policy: Add SECURITY.md with trust model and vulnerability disclosure policy

Fixed

Vulnerability Rules: Fill empty rule fields and add new CVE rules
API: Fix mcp_scan content field and add agent_scan API documentation
Docs: Fix HTML block bold rendering in multilingual READMEs
Architecture: Fix runtime path resolution for local deployments

Changed

Codebase: Convert all Chinese comments and messages to English in api.go and knowledge2_api.go
Docs: Expand Related Papers to 17 entries with 5 new 2026 papers; sync across all multilingual READMEs
Docs: Add architecture evolution document covering v0.1/v2.6/v3.6.0 (#294)
Vulnerability Stats: Update component vulnerability counts, add crewai/kubeai/lobehub entries (#291)