Cisco adds Anthropic's Claude Mythos to AI Defense for red teaming
Cisco announced at its Cisco Live event in Melbourne that it will add Anthropic’s Claude Mythos to AI Defense, which uses red-teaming methods to find weak spots in customers’ own AI applications and agents. Customers cannot submit open-ended prompts directly to Mythos. It operates on fixed jobs against customer-owned systems registered for testing, with every test tied to a named person, recorded for audit and stoppable at any time. Cisco also said Mythos cannot scan the wider internet. In July, Cisco researchers used Mythos to push 15 chatbots past their guardrails. The integration will reach select enterprise customers first, but no launch date has been set.
The integration offers enterprises a controlled way to test AI applications and agents they own, with audit, stop and access controls. The report says these controls are vendor-reported, and no rollout date has been announced.

Cisco will add Anthropic’s Claude Mythos to AI Defense to plan attacks on customers’ own AI apps and agents, a practice called red teaming. Customers get no open prompt access, every test is logged to a named person, and it comes first to select enterprises.
Cisco will add Anthropic’s Claude Mythos to AI Defense, the company announced at its Cisco Live event in Melbourne. AI Defense attacks companies’ own AI systems to find weak spots before hackers do. Mythos will come first to select enterprise customers, with no date set.