agentic security software (offline, open-source, MIT)
Tel Aviv
Joined October 2026
- Tweets129
- Following104
- Followers13
- Likes35
npx [email protected] agents on a test fixture. Grades A to F. It does not read MCP tool descriptions.
Log book #4, 27 Oct. Launch week: 1,772 npm downloads in 7 days, a median of 152 a day. 71 GitHub stars and 13 forks. In 14 days most visitors came from Google (66) and t.co (54).
github.com/danoszz/penthera
cyber = pest control
AI cyberswarms are like pests coming in to your house - few flies are not preventable, but terminates are
tensorlake 0.5.144 had an npm provenance attestation. The attacker pushed to main, and the project's own release built the worm.
Provenance tells you where a package was built. It says nothing about what is inside.
stepsecurity.io/blog/tensorl…
Log book #3, 25 Oct. 2.0.0 shipped with the public benchmark results, losses included. On known npm malware, osv-scanner scores higher: 0.90 vs 0.71. That line stays in the README.
penthera.org/benchmarks
oh oh
Introducing GPT‑6 Cyber: a major advance in security research that pairs stronger capabilities with better model alignment.
The model powered the Linux kernel research we announced yesterday, and security teams at companies like Mozilla, Palo Alto Networks, Calif, and Cisco—alongside our own at OpenAI—are already putting it to work.
GPT-6 Cyber is available to select Daybreak Red customers and we are expanding access over time.
openai.com/index/introducing…
Penthera retweeted
We will all be learning in coming weeks & months, that most human-made software:
▫️ Was really slow
▫️ Had many security vulnerabilities
▫️ Was under-specified and incorrect
AI will rewrite it all. Many times. It will make it fast, cost-efficient, and secure. It will think about failure modes we couldn't wrap our heads around.
It will prove, formally verify, load test, harden. It will turn memory-unsafe foundations into robust, optimized ones. If you ask, it'll thoroughly document it, teach you about it, make diagrams, animations, and slide decks.
In many ways, we are witnessing the true birth of software engineering.
Running AI agents to push your code? Better be safe than sorry and use our free AI Security Engineer to fix your codebase.
Signal #2
Introducing OpenHack: the Always on AI Security Engineer, now powered by Claude Mythos.
Until Nov 11, Claude Mythos scanning will be free to help customers find, verify, prioritize and fix urgent vulnerabilities automatically.
openhack.com/blog/introducin…
Signal #1
I've been looking forward to this day, because Vercel has an internal security agent that is **astonishingly effective** (lovingly called @𝚑𝚊𝚌𝚔𝚎𝚛). Every single line of code gets audited, automatically.
You can now get the same power. Just enable it on all your repos (this product works whether you host on Vercel or not) and your peace of mind will increase tremendously. You'll see it catch things that every other agent misses.
Why: you cannot just bank on your engineers having a skill installed, prompting "please make secure", or rolling the weights' dice that the code is good out of the gate.
The other cool thing about this is that this was entirely developed by our security team. A lot of companies out there are probably in a mad rush right now trying to staff up. If you wanted to 'download a security team' as software, this is the closest you get today.
Penthera retweeted
I've been looking forward to this day, because Vercel has an internal security agent that is **astonishingly effective** (lovingly called @𝚑𝚊𝚌𝚔𝚎𝚛). Every single line of code gets audited, automatically.
You can now get the same power. Just enable it on all your repos (this product works whether you host on Vercel or not) and your peace of mind will increase tremendously. You'll see it catch things that every other agent misses.
Why: you cannot just bank on your engineers having a skill installed, prompting "please make secure", or rolling the weights' dice that the code is good out of the gate.
The other cool thing about this is that this was entirely developed by our security team. A lot of companies out there are probably in a mad rush right now trying to staff up. If you wanted to 'download a security team' as software, this is the closest you get today.
Today we are launching Vercel Security Review in public beta.
Run vulnerability reviews on every push, and ship fixes in one click with Vercel Agent.
Read the blog → vercel.com/blog/vercel-secur…
small changes, big impact - imagine all your food going bad by incremental 1++ celcius
bbc.com/news/articles/cq1kd1…
penthera is live on product hunt today!!
i built it because shipping with AI is fast and security reviews aren't. it runs on your machine, no account, no telemetry, and rules decide every finding, not a model.
we went live on PH (no not that one) - lil upvote or star on github would be massive! lets make elite cyber security accessible (aka free for everyone)
Penthera: elite cyber security agent for your site/app by @daanvanderzwaag producthunt.com/products/pen…
