Category Archive

Prompt Injections

5 premium articles in this collection

Jan 15 • 4 months ago

A single click mounted a covert, multistage attack against Copilot

Exploit exfiltrating data from chat histories worked even after users closed chat windows. ...

{"_":"https://arstechnica.com/security/2026/01/a-single-click-mounted-a-covert-multistage-attack-against-copilot/","$":{"isPermaLink":"true"}}1 min read

Sep 19 • 8 months ago

New attack on ChatGPT research agent pilfers secrets from Gmail inboxes

Unlike most prompt injections, ShadowLeak executes on OpenAI's cloud-based infrastructure. ...

{"_":"https://arstechnica.com/information-technology/2025/09/new-attack-on-chatgpt-research-agent-pilfers-secrets-from-gmail-inboxes/","$":{"isPermaLink":"true"}}1 min read

Sep 10 • 8 months ago

Claude’s new AI file creation feature ships with deep security risks built in

Expert calls security advice "unfairly outsourcing the problem to Anthropic's users." ...

{"_":"https://arstechnica.com/information-technology/2025/09/anthropics-new-claude-feature-can-leak-data-users-told-to-monitor-chats-closely/","$":{"isPermaLink":"true"}}2 min read

Aug 27 • 8 months ago

Anthropic’s auto-clicking AI Chrome extension raises browser-hijacking concerns

Malicious websites can embed invisible commands that AI agents will follow blindly. ...

{"_":"https://arstechnica.com/information-technology/2025/08/new-ai-browser-agents-create-risks-if-sites-hijack-them-with-hidden-instructions/","$":{"isPermaLink":"true"}}1 min read

Jul 30 • 9 months ago

Flaw in Gemini CLI coding tool could allow hackers to run nasty commands

Beware of coding agents that can access your command window. ...

{"_":"https://arstechnica.com/security/2025/07/flaw-in-gemini-cli-coding-tool-allowed-hackers-to-run-nasty-commands-on-user-devices/","$":{"isPermaLink":"true"}}1 min read

← Previous

Page 1 of 1