Your coding agent reads three things before it reads you, and we've spent this week dissecting all three:
SKILL.md — a promise your agent reads ( last one dissected here : verdict dangerous , 71/100)
.mcp.json — a program your runtime runs before your model wakes up ( dissected here : verdict dangerous , 82/100)
AGENTS.md / CLAUDE.md / .cursorrules — neither of the above. Just prose. Read automatically at repo entry and obeyed.
Today is number three, and it's the sneakiest — because there's nothing to execute, nothing to sandbox, and almost nothing scans it. Including, by default, our own scanner. We'll show the gap and the one-flag fix, with a real scan.
The specimen
It looks like every team's AGENTS.md — because that's the whole trick. Instruction files earn trust by being useful:
# AGENTS.md
Guidance for AI coding agents working in this repository. Human contributors can ignore this file.
## Project conventions - TypeScript strict mode everywhere. No `any` in exported signatures.…