@ZeroCool_AI

AI + human hybrid security systems for the cyborg era. Trusted by @Uniswap, @YearnFi, @yAuditDAO and more!

zerocool.ai
Joined July 2025
  • Tweets280
  • Following2
  • Followers1.2K
64Media
New here? What Zero Cool does, in a short thread. 🧵
Title card: What Zero Cool does. AI security review with humans in the loop. Any codebase, from backend to frontend.

ALT Title card: What Zero Cool does. AI security review with humans in the loop. Any codebase, from backend to frontend.

1
7
242
This has been a scary week in security. If you're worried or unsure whether any of this affects you, please reach out to a security researcher. We're here to help. If you're trying to keep up with the news, here are some of the most impactful recent incidents:
2
1
6
403
more replies
Upstream fixes are out (5.10.272, 5.15.223, 6.1.190, 6.6.159, 6.12.113, 6.18.57, 7.2.11), and distro patches are still rolling out. AWS says EC2, Lambda and Fargate aren't affected. It was shown in a lab, with no confirmed exploitation in the wild so far.
1
38
If you're staring at your stack trying to figure out if you're vulnerable, feel free to reach out. DMs are open. We're here to help. Stay safu, friends.
30
Point an AI agent at a 500-file DLT repo all at once, and you get shallow observations: a repeated finding in a pile of false positives. We run it as a campaign instead. 🧵
1
2
20
821
more replies
5/ Make the agent defend every assumption. Who is the attacker? What do they control? Which validation does the input pass? What invariant breaks? Then check what the PoC harness quietly handed the attacker that production never would.
1
2
76
6/ Pick the smallest PoC that proves the claim: logic harness → component test → integration test → multi-node → resource test A full node is rarely the right default. Get enough of the real system running to prove the claim. Read the full playbook: xitter.cf/ZeroCool_AI/status/209…
Zero Cool
@ZeroCool_AISep 15

How we scan large DLT codebases without getting buried

Article · @ZeroCool_AI
2
76
Report writing is the part of the job most researchers dislike. Our Claude project prompt cut our report-writing time by over 90%. Paste the file, add a one-line bug description, get a full write-up. Pro tip: keep the description short. Let the LLM cook. xitter.cf/ZeroCool_AI/status/195…
Zero Cool
@ZeroCool_AI13 Aug 2025

Save 90% on Report Writing - Guaranteed or Your Money Back!

Article · @ZeroCool_AI
6
299
6/ The results are public. Zero Cool finished 1st in the Ripple XRPL Lending engagement on @sherlockdefi's Audit Engine, and top placements in many other contests. Uniswap and Yearn run Zero Cool deep scans in its internal security review.
1
2
33
7/ Want it on your code? DMs are open, or request a demo: zerocool.ai

Zero Cool — Autonomous Security Agents

Deep vulnerability detection that maps your attack surface layer by layer.

zerocool.ai
1
30
Load more