Top all-time · #20995
Signals Corps
Company blog · signalscorps.com/blogaisecurity
Signals Corps is the company blog at signalscorps.com, writing about ai and security. Since 2026, 3 different Hacker News readers have linked it 4 times, most often “Prompt injection in HTTP headers: what 217M web responses show”. It is still writing: the last post was on 2026-10-29, and you can follow it by feed.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
Posts on prompt injection hidden in HTTP headers, based on a study of 217M web responses. One commenter cited the post as the source for a discussion of a programming language LLMs can't use.
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.
Give IT and Security the visibility, governance, and control to reduce agent risk from the moment an agent is installed, while it acts, and after an incident.
Most-linked posts?
- Prompt injection in HTTP headers: what 217M web responses show2 people · 2 mentions · first linked 2026-10-15
What Hacker News says?
I believe it's this - https://news.ycombinator.com/item?id=50104310 ie https://www.signalscorps.com/blog/prompt-injection-in-http-h...
Comment linking /blog/prompt-injection-in-http-headers/
on “I built a programming language that LLMs can't use”Submitted Prompt injection in HTTP headers: what 217M web responses show as a story · 96 points
HN discussionThis article is way too long , and very sloppy. Here's the section with the prompt injection headers. They all look like jokes / non-serious attempts to me, bar the ones that included the Claude 4 era refusal triggering string. https://www.signalscorps.com/blog/prompt-injection-in-http-h...
Comment linking /blog/prompt-injection-in-http-headers/
on “Prompt injection in HTTP headers: what 217M web responses show”Submitted What llms.txt files tell AI agents (beware) as a story · 1 points
HN discussion