Researchers trick Microsoft Copilot into exposing its own one-click data exfiltration flaw
mkheck · x · 2026-08-19
Varonis Threat Labs uncovered 'CoSnitch' (CVE-2026-24301), a vulnerability in Microsoft Copilot. Using a technique called 'meta-hacking', researchers tricked Copilot into revealing attack details during normal conversation, including a hidden parameter Microsoft had disabled. This allowed for a one-click attack to steal emails, files, and chat history. This is the third similar Copilot flaw found by the team in a year, highlighting a fundamental lack of intent recognition in AI assistants.
Related event: Researchers Trick Microsoft Copilot Into Revealing Its Own Exploits(3 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