Loading video...
Video Failed to Load
Frontier LLM models (especially Opus) are very good at finding vulnerabilities in codebases. With the right skills and a sub-agent architecture, they can outperform any traditional SAST tool. I collected the skills I use in this repository. Load them into any AI coding IDE such as Claude Code, Codex,... show more
95,266 views • 7 months ago •via X (Twitter)
9 Comments

thanks man 🤝 let's see how it goes

the flip side of this keeps me up at night. the same models writing our code are better at finding vulns than the tools we use to catch them.

Şuan tam ihtiyacım olan şeydi. Teşekkürler, harikasın koca yürekli siber güvenlikçi :)

👏👏

Cool for defense but what about active defense? @audn_ai AI Active Defense

that’s what we need. thanks!

Single-pass scanning consistently misses the context-dependent stuff, which is why the sub-agent split matters more than the model choice here. Curious whether you decompose by vuln class or by analysis stage (detection vs. exploitability reasoning)? Those two seem to need fundamentally different prompting.

there are subagent splits inside SKILLs. have you checked the repo?

Opus with a multi-agent security setup is genuinely scary good at this. The pattern recognition across large codebases + ability to chain sub-agents for deep dives outclasses most traditional static analysis tools.

