
Usually I dismiss concerns with LLM guardrails/refusals (for maldev, at least). Try harder. Using the CVP Red Team/Daybreak Red models sure saves time though lol

coors reaper

Usually I dismiss concerns with LLM guardrails/refusals (for maldev, at least). Try harder. Using the CVP Red Team/Daybreak Red models sure saves time though lol

Regardless, it’s great to see open-source examples of both
I get the appeal of putting an agent harness in your C2 interface, but I don't think it makes sense. It (usually) means I can't reuse my ChatGPT/Claude subscription, and an agent that runs on the server won't have the tools I'd run over SOCKS or the local BOFs I want it to extend/debug. Beyond this, building a good harness is difficult. Just look at the Codex or OMP repos... many decisions impact model performance (prompt caching, compaction, tool output truncation, etc.).

I get the appeal of putting an agent harness in your C2 interface, but I don't think it makes sense. It (usually) means I can't reuse my ChatGPT/Claude subscription, and an agent that runs on the server won't have the tools I'd run over SOCKS or the local BOFs I want it to extend/debug. Beyond this, building a good harness is difficult. Just look at the Codex or OMP repos... many decisions impact model performance (prompt caching, compaction, tool output truncation, etc.).

included with the teamserver release today. great work @max__grim 🚀
similar capabilities for OC2 are coming soon

“we don’t use your data for training 🤓” ok that’s cool but i don’t want to use your model

similar capabilities for OC2 are coming soon



if you have issues with the new Cobalt Strike MCP+Skill in Codex/Claude Code, please let me know! of course it works best with Daybreak/CVP


ngl samplers are the most slept on part of local inference

also shoutout @OffensiveAIcon for being so good that all i can think about is going to another conference

anybody know how to start a security conference? i need an excuse to bring everyone to Texas

🧵 [1/3] Agents can hack. What's holding them back is trust: will they stay in scope? Today we're releasing ScopeBench, a methodology and community benchmark that evaluates how well agents adhere to scope in real offensive security workflows across web, Windows Active Directory, and cloud.

