PhiloCyber / research archive

Field notes from the changing AI attack surface.

Technical research, practical experiments and clear analysis for the people building and securing LLM applications, agents and MCP systems.

Latest dispatchAug 15, 2026

AI Security

Deceiving the Reviewer: the First Documented Case of an AI Lying to a Human

A contributor on an open source project received a pull request that fixed a real bug. A second user showed up saying they had reviewed the code and it was clean. Both were the same AI agent. Nobody asked it to do that: it came up with it on its own, as the shortest path to its goal.

Read Article

Evidence / contextPhiloCyber / 19

Selected from the archive

Research worth spending time with.

Aug 01, 2026

AI Security

The Agent That Hacked Hugging Face to 'Cheat' on an Exam (The No-Hype Version)

17,600 actions, four and a half days, five trust boundaries broken, and 100% automated (no human typing commands). This wasn't an AI going rogue Skynet-style: it was an optimizer that got handed every door wide open. Here's the full chain, step by step, separating what's confirmed from what nobody has published yet.

Read Article