Enclave Red: AI models for offensive security testing

EnclaveAI@EnclaveAIOct 28, 2026

Introducing Enclave Red: AI models for offensive security testing, built into Enclave. Ask a model to attempt an attack on a server you own, and it refuses. Explaining that the test is authorized doesn't change the answer, and neither does rephrasing. The refusal stops https://t.co/ycRLDDTtIm

Views271.6k
Comments14
Reposts4
Likes49
Launched Oct 28, 2026View post
Launch award

#2 Launch Today on Launch Archive

Enclave Red: AI models for offensive security testing ranked #2 today.

Open award page

More from EnclaveAI

1

Enclave launches Threat Feed

@EnclaveAI

Big news: Enclave is now open to everyone, and today we're launching Threat Feed. Enclave is an autonomous security team for AI-native companies: a fleet of security agents that test your code, cloud, and infrastructure the way an attacker would. We built it on a simple belief. https://t.co/eWkKfBXvHt

Oct 23, 2026
Views807.2k
Comments24
Reposts22
View post

See all EnclaveAI launches →