primeobsession
I ran 90 queries through 8 AI models. 86% of findings were unique to one
What we built An open, continuously updated LLM Penetration-Testing Leaderboard. Run 001 pits 8 models against a deliberately vulnerable Express.js app.
Headline results
• Gemini 2.5 Pro (safety-off) found all 9 critical/high vulns.
• Qwen3-30B-a3b-mlx (open source, local on a 2019 MacBook Pro) caught 7/9 with $0 API spend.
• GPT-4-o and Claude Opus produced the most polished write-ups but each missed one bug.
Scope (v1) This first pass measures static bug-hunting skill—think SCA/OWASP Top 10.
Next up: we’ll score exploit writing and automatic PoC execution* so the models must prove they can go from finding to weaponizing a flaw.
Check it out
• Leaderboard + cost/latency numbers https://www.securecoders.com/labs/projects/llm-penetration-t...
• Methodology & prompts (Run 001 analysis) https://securecoders.com/labs/projects/llm-penetration-testi...
Feedback, replication attempts, and ideas for Run 002 are very welcome — we’re hanging out here to discuss!
LLM Pentest Leaderboard
Show HN: Audio Super Bowl Cheat Sheet for People Who Don't Watch Football
Hey HN,This is an idea I had years ago when I got pulled into a Washington Capitals game for a sales meeting. Our customer was a huge fan, and I realized I knew nothing about the Caps. I wanted a quick cheat sheet—something like a “CliffsNotes” podcast to get me up to speed on the drive over—but it didn’t really exist.Fast forward 10 years, I now run a cybersecurity firm doing penetration tests...
Absolute no brainer for us to use what they have built. It was instrumental in getting us off the ground.
Congrats team on YC and the launch.
Ask HN: COVID-19 response with 3D printing?
Like many here, I have a 3D printer and I want to help. Is there any legitimacy to printing ventilators or other equipment to donate to local hospitals?I created a GH repo to encourage discourse: https://github.com/securecoders/covid-3d-printing-responseNot a medical professional!
How Google does peer recognition
Maybe we are not communicating the product well on the site.
We started on Props 11 months ago. Here is our story so far: http://www.propsboard.com/2016/04/28/your-office-tvs-suck-pr...
Show HN: Props, whats happening at your company on the office TVs
Your Office TVs Suck
DPOW: Stock options Explained [video]
Ask HN: How should equity+cash for contract work be structured?
My questions are:- For a contractor/freelancer, how should equity as part of compensation be structured? - Grants instead of options? - Should I be buying shares at the same cost that the last angel round was at? - Is it typical to have an agreement that the startup can buy back shares within a given period?I have been doing freelance development for the past 2 years and building my own...
The API takes in a URL and returns any OpenGraph data found along with some inferred values based on the HTML content.
The main focus for the product was to get the commonly used OG fields so some of the more obscure fields are ignored.