No signal event on file yet — status is unknown, not "quiet".
- first observed Kanon started keeping permanent history for this agent
- Breaking out Breaking out detected
| Machine-callable | — | unknown | — |
| Open source | 1 | verified | 1 quote(s) |
| Self-hostable | — | unknown | — |
| Bring your own key | — | unknown | — |
| Autonomy level | — | unknown | — |
| Pricing model | — | unknown | — |
| Integrations | — | unknown | — |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
As AI security becomes a critical concern, this platform offers a structured red teaming capability tailored for large organizations and high-compliance environments.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
FAQ
What is AI-Infra-Guard?
AI-Infra-Guard is a full-stack AI red teaming platform from Tencent that evaluates AI systems for security risks through agent scans, skill assessments, MCP checks, and LLM jailbreak testing.
What does AI-Infra-Guard do?
To conduct systematic security testing on AI systems to identify potential jailbreaks and misuse vulnerabilities.
Why does AI-Infra-Guard matter?
As AI security becomes a critical concern, this platform offers a structured red teaming capability tailored for large organizations and high-compliance environments.
Is AI-Infra-Guard open source?
Yes — AI-Infra-Guard is open source.
How popular is AI-Infra-Guard?
As tracked by KanonAgent: 1.9k upvotes (first indexed 2026-08-20).
When did AI-Infra-Guard take off?
KanonAgent flagged AI-Infra-Guard as breaking out on 2026-08-21 on GitHub (at 373 stars/day that moment). The breakout log is append-only: https://kanonagent.com/rising
What are the best AI-Infra-Guard alternatives?
Similar AI agents tracked by KanonAgent: Hidden Business, Audn.AI, strix, pentagi, securenow.ai, AutoCVE.