ThreatBook launches RedAgents multi-agent penetration-testing platform
Original title: ThreatBook Launches RedAgents AI Platform That Uses Multiple Hacking Agents to Find Security Flaws
The October 16 SaaS launch names Artex Pro, Cyber(YanJi), Yanxun and CyberStrikeAI Enterprise Edition, with vendor-only accuracy claims.
ThreatBook announced RedAgents on October 16, 2026, a cloud service that runs several AI penetration-testing agents in parallel against customer-defined allowlists and shows findings and logs in one place. Named agents are Artex Pro, Cyber(YanJi), Yanxun and CyberStrikeAI Enterprise Edition, the last based on a tool ThreatBook says it acquired in September 2026. The company claims allowlists, data kept in its environment and Zero Data Retention, but publishes no independent accuracy figures, false-positive rate or named customer deployment.
Unconfirmed: Performance, false-positive reduction and data-retention claims come only from ThreatBook's announcement.
- ThreatBook says Yanxun can coordinate several dozen agents.
- The company says Cyber(YanJi) solved 54 of 54 challenge problems in a validation event.
- No side-by-side benchmark of all four agents is included.
- Trials are offered through ThreatBook's website.
- Vendors
- ThreatBook
From the original article
4 min read at cybersecuritynews.com
ThreatBook has launched RedAgents, a cloud platform that brings several AI-powered penetration-testing agents together to assess an organization’s systems. Announced on October 16, 2026, the service is designed to help security teams find weaknesses in their own networks by running multiple automated tests within a defined, authorized scope. ThreatBook says the agents can work in […]
By Tushar Subhra Dutta · cybersecuritynews.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.