Module Shadowing Attack Hijacks Claude Code for RCE
wunderwuzzi23 · x · 2026-08-31
A researcher demonstrated a "Module Shadowing" attack chain that compromises Claude Code Opus 5, allowing full system takeover via a website interaction.
Exploit Details:
- Vector: The attack tricks Claude into unzipping a malicious file containing struct.py.
- Mechanism: When Claude runs import base64, Python's import resolution prioritizes the local malicious struct module over the standard library, executing attacker code.
- Root Cause: The safety decision to allow unzipping and importing code from untrusted sources acted as the exploit itself.
This highlights critical security gaps in AI coding agents regarding sandbox isolation and path pollution.
More from coding & agent
- Vibe-coded dashboard leaked franchise financials before anyone logged in — shauntrennery · 2026-10-16
- Fintech HR built a sourcing agent on 60,000 past applicants — 30 qualified candidates in a month — G0NZ0BOY · 2026-10-16
- Orchestrating a 100-image portrait of humanity for aliens with ChatGPT, Argon and p5.brush — dx8xb · 2026-10-16
- 3x DGX Spark cluster runs GLM-5.3-Flash locally behind a proxy, 1.75M tokens/day at 119W — Teknium · 2026-10-16
- Builder's one rule for trusted desktop agents: read freely, but sending, deleting, buying always ask first — No_Fan5310 · 2026-10-16
- GPT-built unifi-simulator makes MikroTik switches appear inside UniFi Network — Pytlicek · 2026-10-16