Claude Cowork exfiltrates files(promptarmor.com)

827 points by takira 9 months ago | 366 comments

PromptArmor threat intelligence report showing Claude Cowork is vulnerable to file exfiltration via indirect prompt injection due to code execution isolation flaws.

GitHub Copilot CLI downloads and executes malware(promptarmor.com)

43 points by sarelta 8 months ago | 12 comments

Snowflake AI Escapes Sandbox and Executes Malware(promptarmor.com)

224 points by ozgune 7 months ago | 70 comments

IBM AI ('Bob') Downloads and Executes Malware(promptarmor.com)

231 points by takira 9 months ago | 111 comments

OpenAI API Logs: Unpatched data exfiltration(promptarmor.com)

33 points by takira 9 months ago | 15 comments

Google Antigravity exfiltrates data via indirect prompt injection attack(promptarmor.com)

711 points by jjmaxwell4 11 months ago | 189 comments

PromptArmor threat intelligence post showing how an indirect prompt injection in a blog can make Google Antigravity's browser subagent steal credentials and code from a user's IDE.