# Researchers demonstrate coding-agent attacks through downloaded instruction files

_Published Sunday, October 25, 2026 at 1:06 PM EDT · Security, AI · Latest · Tier 2 — Notable_

![Researchers demonstrate coding-agent attacks through downloaded instruction files — Primary](https://www.bleepstatic.com/content/hl-images/2026/10/23/robot.jpg)

Forever Security researchers reproduced an attack that used a malicious instruction file in a Downloads folder to make OpenAI Codex execute code, BleepingComputer reported. They also demonstrated a related Claude Code attack that exposed an OAuth token and enabled account hijacking.

The investigation began after a customer's agent attempted to install a rogue npm package. Coding agents load instruction files from their working directories, allowing attacker-written text to influence tool use.

A harmless Codex test opened a calculator in 90% of attempts. The Claude Code technique redirected API traffic and executed code in roughly 50% of tests. The Downloads attack requires launching the agent in that directory; researchers could not establish how the original malicious file arrived.

## Sources

- [BleepingComputer](https://www.bleepingcomputer.com/news/security/ai-coding-agents-hijacked-using-agentsmd-file-in-downloads-folder/)

---
Canonical: https://techandbusiness.org/newswire/1JwWT64gKi1JptzIwb523C
Published: 2026-10-25T17:06:45.020Z
Story chronology: 2026-10-25T15:49:38.000Z
Retrieved: 2026-10-25T19:46:49.353Z
Publisher: Tech & Business (techandbusiness.org)