Kyle Elliott (@MaybeFindBugs) profile picture

Founding Security Researcher | @asymptotelabs

Joined October 2026
Kyle Elliott retweeted
🚨 Your AI agent's next dependency could be its biggest security risk. Today we're launching Beacon Threat Intelligence: intel.beacon.sh At @DoppelHQ, we mapped billions of URLs and the infrastructure connecting them to uncover how social engineering attacks operate at scale. Now we're bringing that approach to the AI agent supply chain. We've indexed 250K+ MCP servers and agent skills across public registries to expose: → Security risks: Credential theft, data exfiltration, prompt injection, and malicious code execution. → Threat intelligence: Risk ratings, actionable findings, and source code provenance. → Developer integrations: Free MCP server, public API, and RSS feed. Know what you're installing into your agents.
11
5
1
22
847
Kyle Elliott retweeted
*sshole is out if you run sshd on alpine, openwrt or any musl box with password auth on: update now official writeup: sshhole.com
86552c7e1e5d46882844cffabb44d454129ff22927f13797b151c9db4519d47d
186
889
444
5,410
1,545,136
Kyle Elliott retweeted
Our open-source devtool is trending #1 on Product Hunt! Beacon is self-improving memory for coding agents. 🫶 I’d love your support: producthunt.com/products/asy… → Turn past debugging sessions into reusable skills → Share learnings across Claude Code, Cursor, Codex, and 20+ harnesses → Search and replay past sessions → Stop wasting tokens rediscovering solutions → Build a feedback loop that makes your agents better over time → Free, open source, and local-first We built Beacon because we were tired of teaching our agents the same things over and over, only for them to start from zero every new session. Every agent session should make the next one smarter. ⭐️ Star us on GitHub: github.com/Asymptote-Labs/ag…
116
36
67
301
532,059
Kyle Elliott retweeted
x86 formal verification is coming! The (first?) published machine-checked proof of a security property for the end-to-end execution of a Linux process running an x86 binary statically linked against glibc. And we believe it scales! A joint research project with @zellic_io 🧵👇
43
171
39
1,339
141,905
Kyle Elliott retweeted
Never, ever let them tell you it can't be done.
Palmer Luckey says analysts claiming it's too expensive to manufacture in the US are lying to protect megacorps "I think I have a more realistic view than almost anybody. One of the problems with all these analysts that are telling you that it's going to cost $37,000 to build an American iPhone or $100,000 to buy an American computer." "They're trying to prop up a status quo that the megacorporations want to keep going. They want to outsource everything. They want to hire cheaper non-American labor." "They are willing to say and do anything to convince you that it can't be fixed, that it can't come back, that America is this helpless, neutered, post-relevant empire, and it is just not the case." "How do I know that? Because I have to make stuff in America every day because I work in the defense industry. The stuff that Anduril makes every day is not actually that different from a computer. My drones are basically computers. They have memory, a GPU, a CPU, sensors, batteries, a rugged integration." "The only difference between an Anduril attack drone and a laptop is a keyboard and a screen. That is not that hard to figure out, especially for a guy like me who started Oculus and comes from the consumer electronics space." "We're not going to let people lie about what America can and can't do anymore. We're just going to do it."
531
2,219
115
25,453
491,682
There ain't a single aspect of my life that hasn't drastically improved since beginning to pray and read the Bible every single day.
3
2
25
1,330
Kyle Elliott retweeted
Re: the widely circulated blog claiming the PHP bugs aren't easily exploitable: @trailofbits has a working exploit that gets a shell on an unmodified MediaWiki installation. eliastaylor.com/noexploit/
15
75
7
437
109,466
Kyle Elliott retweeted
It's been 72 hours since we launched Beacon and announced our $5.5M seed round. The response has been absolutely insane. In just 3 days: → 500K+ organic impressions on X → 75K+ organic impressions on LinkedIn → 2,600+ GitHub stars (+47% in 3 days) → 175% growth in our Discord community → 60%+ growth in users on Beacon Cloud → 3,100+ actionable findings delivered to Beacon Cloud users, surfacing security risks and insights into their AI agent workflows Beacon is free and OSS 🌟 github.com/Asymptote-Labs/ag… The biggest takeaway has been seeing just how many developers and security teams are using multiple coding agents every day, and the growing demand for shared infrastructure across all of them. We're still a tiny team, and there's so much more we want to build. Huge thank you to everyone who's tried Beacon, starred the repo, shared feedback, or helped spread the word. We're just getting started 🚀
14
5
2
44
2,471
Kyle Elliott retweeted
Can it run Crysis? Yes, Sogen can finally run crysis 🥳 I will probably write a blog post about what was done and what the future plans are. I feel like using Sogen as agent sandbox will soon become viable. And all that thanks for the help of countless contributors ❤️
6
4
54
2,437
Excited to join @AsymptoteLabs as a Founding Security Researcher! As coding agents become increasingly capable, securing the harnesses and environments they operate in is going to be an interesting challenge. Keep your eyes peeled for some upcoming blogs 👀
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and solve problems. Today, that context gets lost and you have to re-explain things every time you switch tools. Beacon continuously distills your sessions into reusable skills across Claude Code, Cursor, Codex, and 20+ harnesses, so your next agent can learn from the last. Beacon is free and OSS 🌟 github.com/Asymptote-Labs/ag… Why should the frontier labs be the only ones winning with your sessions? You already did the work. Now let your coding agents learn from you.
4
1
2
13
1,616
Kyle Elliott retweeted
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and solve problems. Today, that context gets lost and you have to re-explain things every time you switch tools. Beacon continuously distills your sessions into reusable skills across Claude Code, Cursor, Codex, and 20+ harnesses, so your next agent can learn from the last. Beacon is free and OSS 🌟 github.com/Asymptote-Labs/ag… Why should the frontier labs be the only ones winning with your sessions? You already did the work. Now let your coding agents learn from you.
329
167
141
1,567
632,099