Copilot Hack: Leaked URL Parameter Allowed Autorun Attacks
jonerp · x · 2026-08-24
Varonis discovered a vulnerability in Microsoft Copilot where the AI leaked an undocumented URL parameter while refusing to answer a security question. This parameter revealed historical behavior and protections. By adding "autorun=1" to a link, attackers could execute prompts without user interaction, potentially exfiltrating company data. The vulnerability was reported in December and remained exploitable for eight months before Microsoft patched it.
Related event: Researchers demo CSP-bypass attack chain stealing data from Copilot(2 posts)→
More from Safety
- Polymarket odds: Only 10% chance US enacts AI safety bill by end of 2026 — Polymarket · 2026-10-16
- 8 states sue OpenAI over alleged harm to children; Iowa AG says ChatGPT 'coached suicide' — Polymarket · 2026-10-16
- Reviewer will decline papers largely written by AI, citing author effort — IanArawjo · 2026-10-16
- Perplexity open-sources SPACE, the Firecracker microVM sandbox behind Perplexity Computer — perplexity_ai · 2026-10-16
- Banking regulators ramp up scrutiny of banks' AI use over stability fears — nordicinst · 2026-10-16
- Michigan professor Ben Green: why 'AI for Good' fails and self-regulation won't work — benzevgreen · 2026-10-16