# 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.

Repository: https://github.com/Tencent/AI-Infra-Guard
Canonical: https://ross.abutalabs.com/products/ai-infra-guard
Homepage: https://tencent.github.io/AI-Infra-Guard/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agent, llm, scanner, security, vulnerability, agent-security, ai-red-teaming, ai-security, llm-jailbreak, llm-security, ai-infra, mcp-scan, skill-scanner, llm-evaluation, openclaw-security, prompt-security, prompt-injection, skills-security, security-tools
Last push: 2026-08-26T13:48:13+00:00

## Health v2 (maintenance only)
Score: 88/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 99, longevity 44
- inputs: {"age_days": 616, "days_push": 7, "days_rel": 7, "gap_med": 7.0, "n_releases_24m": 55}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5984, forks 546 (observed 2026-08-28T04:09:33.923347+00:00)

## What it is
Tencent's full-stack AI red teaming platform that scans AI infrastructure, agents, MCP servers, and skills for vulnerabilities and evaluates LLM jailbreak resistance. It is self-hostable via Docker and provides a web-based security assessment service.

## Use cases
- scan AI infrastructure for known vulnerabilities
- test LLM jailbreak resistance
- audit MCP servers for security issues
- find prompt injection vulnerabilities in agents
- red team AI applications before deployment
- assess security of agent skills

## When to choose
- you need automated security scanning of AI stacks and agent tooling
- you want to evaluate LLM robustness against jailbreaks and prompt injection

## When to avoid
- you need general-purpose web application penetration testing
- you only need model quality benchmarks rather than security testing

## Facets
- artifact type: application
- maturity: active
- function: penetration-testing, vulnerability-scanning, security, llm-inference, agent-framework, mcp
- domain: security, artificial-intelligence, large-language-models, penetration-testing
- platform: python, self-hosted
- tags: ai-red-teaming, llm-jailbreak, prompt-injection, mcp-scan, agent-security, ai-agents, docker, web-server

## Member repositories
- Tencent/AI-Infra-Guard (main) score 88

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:33.923347+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:49:52.663987+00:00, confidence not recorded.
  - readme: https://github.com/Tencent/AI-Infra-Guard (fetched 2026-08-28T04:09:33.923347+00:00, sha ddc1bc4e196e)
- Data as of 2026-08-30T08:39:29.467469+00:00.