Tencent/AI-Infra-Guard

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.

71
/ 100
Verified

Combines multi-agent automated scanning with supply chain vulnerability detection (including real-time CVE/GHSA database updates and compromised dependency identification) to assess AI agent workflows across platforms like Dify and Coze. The architecture uses a task-based execution model with immediate termination support and integrates directly with OpenClaw via the `aig-scanner` skill, while supporting Docker deployment with configurable backend services for distributed scanning capabilities.

3,206 stars. Actively maintained with 144 commits in the last 30 days.

No Package No Dependents
Maintenance 25 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

3,206

Forks

321

Language

Python

License

Last pushed

Mar 12, 2026

Commits (30d)

144

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/Tencent/AI-Infra-Guard"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.