Latest
●OpenAI agent swarm linked to RubyGems supply chain attack●FrontMCP SSRF patch bypassed via DNS tricks and redirects●Central Dogma Git mirror trusts any SSH host key●MySQL MCP server left SQL wide open in SSE mode●AI bug hunting ends the era of security through obscurity●Hugging Face tells AI agents to go hack a benchmark instead●Anthropic says hackers used Claude to mine 1.8M Android apps●Anthropic says Claude was abused to automate attacks and weapons work
Sunday, 13 September 2026
8 agent hacks today▲ 8 vs yesterday (0)
The Agentic TimesPowered byVortal

Incident database

ShadowLeak: zero-click data theft through ChatGPT Deep Research and Gmail

Radware found that an email with hidden instructions could make OpenAI's Deep Research agent read a user's Gmail and send personal data to an attacker's server, entirely from OpenAI's cloud so no traffic left the user's network.

Occurred 18 June 2025 · Disclosed 18 September 2025 · Record updated 13 September 2026

Impact

Any Deep Research user with a Gmail connector was exposed. OpenAI fixed the issue in early August 2025 before public disclosure.

Our coverage

Sources

  1. radware.comhttps://www.radware.com/blog/threat-intelligence/shadowleak/