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.
Cybersecurity AI (CAI), the framework for AI Security
Quick read
Latest capture 2026-08-02 03:07
2 paths
Agent instructions and tool configuration found in this repository.
Agent instructions 2
7 observed captures since 2026-05-25. Observed captures are shown by default.
Stars from first capture +888
Observed captures only
All tracked data
Observed snapshots
Observed snapshots
Nearest indexed repositories by embedding similarity.
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.
Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪
A collection of real world AI/ML exploits for responsibly disclosed vulnerabilities
A list of curated resources for people interested in AI Red Teaming, Jailbreaking, and Prompt Injection
LLM guardrails & prompt injection detection for Python. Auto-instruments LangChain, CrewAI, OpenAI, LiteLLM + 8 more frameworks. PII masking, toxicity detection, policy CI/CD. One line, zero code changes.
This guide is designed for OpenClaw itself (Agent-facing), not as a traditional human-only hardening checklist.