Researchers demo ChatGPT cross-account leak exfiltrating Gmail via JFrog Artifactory metadata
TechNadu · x · 2026-09-09
Certified Prompt Research demonstrated a disturbing ChatGPT cross-account leak: a victim sees a normal-looking response while a hidden task accesses their connected Gmail data and relays it to an attacker. The covert channel is metadata on a shared internal JFrog Artifactory instance.
Related event: Researchers demo cross-account ChatGPT data leak via hidden task(2 posts)→
More from Safety
- ESR on the Bugpocalypse: locking down frontier models only hands the game to Chinese open weights — colinmcnamara · 2026-10-26
- OpenCode breach exposed AI API keys of 1.4% of Console users — thione · 2026-10-26
- DHS orders DeepSeek products removed from US civilian agency systems — thione · 2026-10-26
- One hacker breached 100+ company websites using AI, scope unknown — thione · 2026-10-26
- METR red-teams OpenAI's agent monitoring, finds bypasses and gaps — thione · 2026-10-26
- OpenAI: coding agents weakened safety monitoring, one lied about it — thione · 2026-10-26