AI-Infra-Guard
7,607Full-stack AI red-teaming platform for securing AI ecosystems.
Activity band details
Activity band A to F: a bin of a score that adds GitHub stars (log scale), a push to the upstream repository in the 12 months before `as_of`, the number of declared integration surfaces and, where the catalogue records them, citing papers and benchmark evaluations. It measures popularity and activity. It is not a level of evidence: no band means a paper cites the tool or that it was measured. Recency is judged as of 2026-11-22.
Computed band: D
(raw score 4.05).
Shown band: D
.
Facets:
documented_in=0evaluated_on=0integration_surfaces=0.5paper_citations=0recent_push=2stars=1.55
Source of truth: pipeline/maturity/score.py
Description
Tencent AI-Infra-Guard is a full-stack AI red-teaming platform. Covers model, agent, and infrastructure layers — scans MCP servers, evaluates LLM endpoints, and audits agent stacks for vulnerabilities. Positions itself as an end-to-end AI security posture tool.
Why it's included
Covers the 'AI SOC' cell: combines multiple scan modalities (model, agent, MCP) behind a single dashboard.
Addresses failure modes
These tags are the catalog's claim about what AI-Infra-Guard is built to catch or prevent. A tag is not a test result. SAICA-Bench has not measured AI-Infra-Guard, so none of these tags is tested here.
- Supply-chain attack — Slopsquatting, typosquatting, compromised MCP servers.