News for hackers. Stuff that matters.

A comment on Show HN: Output.ai - OSS framework we extracted from 500+ production AI agents. Parent comment

Re:Show HN: Output.ai - OSS framework we extracted from 500+... by marcosmarxm on Tuesday April 07, 2026 @11:24AM (#47676830)
Do you mind sharing any content from your team's research? I've recently gotten interested in agent/llm attacks and how to protect against them.
[ Parent | on HN ]
Re:Show HN: Output.ai - OSS framework we extracted from 500+... by stevenkoze02 on Tuesday April 07, 2026 @02:57PM (#47679765)
We've published 5 papers covering different attack surfaces in the AI agent ecosystem: https://agentsid.dev/research

The most relevant to what you're asking about is "Invisible Ink" (invisible Unicode smuggling in MCP tool descriptions, GPT-5.4 follows hidden instructions 100% of the time) and "Weaponized by Design" (census-scale analysis of 15,982 MCP servers, 137,070 findings). Both have full methodology and reproducibility details.

The scanner is open source if you want to test against your own stack: npx @agentsid/scanner

[ Parent | on HN ]