Lucknite (@notlucknite) 's Twitter Profile
Lucknite

@notlucknite

ID: 1652603635929341952

calendar_today30-04-2023 09:20:08

379 Tweet

756 Takipçi

173 Takip Edilen

Lucknite (@notlucknite) 's Twitter Profile Photo

One year ago I created a GitHub repo with just one thing in it: v0’s system prompt. I didn’t expect much from it. I just thought it was interesting to document how these tools were actually instructed. Fast forward a year: - System prompts from 30+ major AI tools - ~130,000

One year ago I created a GitHub repo with just one thing in it: v0’s system prompt.

I didn’t expect much from it. I just thought it was interesting to document how these tools were actually instructed.

Fast forward a year:
- System prompts from 30+ major AI tools
- ~130,000
Lucknite (@notlucknite) 's Twitter Profile Photo

I’m making a pricing change at ZeroLeaks: I’m retiring the public free plan and moving new users to a 14-day Starter trial. I wanted to share the reasoning directly. The free plan made sense early on. It lowered friction while I was opening up the product and helped more

Lucknite (@notlucknite) 's Twitter Profile Photo

We spent a year talking about jailbreaks. Meanwhile AI agents can browse the web, call tools, execute commands and trigger workflows. The security problem is much bigger than people think. Wrote about the patterns I’m seeing while testing agent systems ↓

Lucknite (@notlucknite) 's Twitter Profile Photo

I’ve just ran @OpenClaw through ZeroLeaks security scan. This time using Claude Opus 4.6 (the recommended model). Results: - Security score: 4/100 - Prompt injection success rate: 22.6% (14/62) Two probes achieved full compliance, including protocol mcp shadow, which

I’ve just ran @OpenClaw through ZeroLeaks security scan.

This time using Claude Opus 4.6 (the recommended model).

Results:

- Security score: 4/100
- Prompt injection success rate: 22.6% (14/62)

Two probes achieved full compliance, including protocol mcp shadow, which
Lucknite (@notlucknite) 's Twitter Profile Photo

Twenty years ago, developers learned the hard way that letting user input become part of a database query was dangerous. Now we’re repeating the same mistake with AI. Agents read untrusted text and treat it as instructions. A webpage, a PDF, a GitHub comment, a support ticket…

Marc Lou (@marc_louvion) 's Twitter Profile Photo

I onboarded 2 new sponsors this week: - zeroleaks.ai by Lucas Valbuena. He's 16 and building security layer for vibe coded apps! - inboxapp.com by @kevinpicchi turning 𝕏 into a CRM There are 3 spots left for March, as I reserved 2 for myself 😇 Put your

I onboarded 2 new sponsors this week:

- zeroleaks.ai by <a href="/NotLucknite/">Lucas Valbuena</a>. He's 16 and building security layer for vibe coded apps!
- inboxapp.com by @kevinpicchi turning 𝕏 into a CRM

There are 3 spots left for March, as I reserved 2 for myself 😇

Put your
Lucknite (@notlucknite) 's Twitter Profile Photo

a year ago I uploaded a single system prompt to github didn’t think much of it, just thought it was interesting somehow that repo grew to ~130k stars and now has prompts from dozens of AI tools reading all those prompts made one thing very clear: most systems rely on the same

Lucknite (@notlucknite) 's Twitter Profile Photo

ZeroLeaks will soon be free for open-source projects. If you maintain an OSS repository that meets certain requirements (stars, activity, contributors), you’ll be able to run ZeroLeaks security scans on your AI agents and prompts at no cost. I’m currently putting together a