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
- Anthropic red team's first-ever model "abliteration" cut GLM-5.3 refusals from 90% to 3% for ~$4,400 — cephaloform · 2026-10-16
- Anthropic grants METR employee-like access as independent safety evaluators go public — AnthropicAI · 2026-10-16
- APEX-Harm benchmark: script-based injection attacks easily compromise agents in shared workspaces — KAUST · 2026-10-16
- Residual-stream forecasts predict agent violations before they happen, USC study shows — USC · 2026-10-16
- AI safety drama: risk research called a 'company effort,' team lead responds — logangraham · 2026-10-16
- Brave's Leo adds end-to-end encrypted chat with GLM via attested TEE — gnukeith · 2026-10-16