Top all-time · #16988
Knostic
Company blog · knostic.ai/blogsecurityai
Knostic is the company blog at knostic.ai, writing about security and ai. Since 2024, 4 different Hacker News readers have linked it 7 times. It is still writing: the last post was on 2026-10-27, and you can follow it by feed.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
HN readers link Knostic's blog for its post on zero-width Unicode characters, which can make a malicious domain look identical to a real one. Its OpenAnt vulnerability-discovery release is also discussed.
Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Secure Claude Code, Cowork, MCP servers, and skills, so your business can adopt AI agents as fast as it wants to, without losing control of what they reach.
What Hacker News says?
It can be visually identical to the real domain. https://www.kicksecure.com/wiki/Unicode It's also happened with code pushes on GitHub, which didn't get caught in code review, and has compromised build processes by introducing a malicious domain that is visually identical. Sounds like a HN-type problem. https://www.knostic.ai/blog/zero-width-unicode-characters-ri...
Comment linking /blog/zero-width-unicode-characters-risks
on “Gaming on Linux has never been more approachable”Submitted Exposed MCP servers across the internet as a story · 80 points
HN discussionKnostic is open-sourcing OpenAnt, our LLM-based vulnerability discovery product, similar to Anthropic's Claude Code Security, but free. It helps defenders proactively find verified security flaws. Stage 1 detects. Stage 2 attacks. What survives is real. Why open source? Since Knostic's focus is on protecting agents (not vulnerability research), we're releasing OpenAnt for free. Plus, we like open source. ...And besi…
Comment linking /blog/oss-scan
on “OpenAnt: OSS Vulnerability Discovery (no one wants to compete with Anthropic)”Submitted DeepSeek's cutoff date is July 2024: We extracted DeepSeek's system prompt as a story · 8 points
HN discussionSubmitted A New Class of AI Attacks: LLM Flowbreaking as a story · 3 points
HN discussionSubmitted OpenAnt: OSS Vulnerability Discovery (no one wants to compete with Anthropic) as a story · 1 points
HN discussion