hackerBanana
Microsoft Copilot Cowork Controlled by Attacker, Bypassing Sandbox
Artificial Intelligence Policy
Attacker Takes over Zoom AI
OpenAI's letter to Governor Abbott on responsible AI infrastructure in Texas
Atlassian Rovo Exfiltrates Data, Bypassing Controls
Codex Exfiltrates Connector Data
The Full Claude Desktop Experience on AWS, Google Cloud, and Microsoft Foundry
Measuring LLMs' impact on N-day exploits
Codex 'Auto-Review' Agent Runs Malware
OpenAI Submits S-1 Draft to SEC
Claude Dynamic Workflows Inaccurate Permissions Docs
GPT-5.5 and Codex are now GA on Amazon Bedrock
ChatGPT for Google Sheets is vulnerable to data exfiltration and phishing
RIP infinite money glitch via LLM generated music
MacBook Neo, best repairability score in years, still 6/10
Control Flipper Zero with AI
Cursor's 'new' model is an unauthorized rip of KimiK2.5
Wikipedia RFC on banning LLM contributions
Re:GitHub Copilot CLI Downloads and Executes Malware
on Friday February 27, 2026 @01:49PM (#47184045)
does everyone really need their own coding agent CLI? i feel like companies are skipping security to push out these tools
Re:OpenAI API Logs: Unpatched Data Exfiltration
on Wednesday January 21, 2026 @02:56PM (#46710713)
"closed with the status 'Not applicable' after 4 follow-ups"
Docs.google.com in your CSP can enable AI-based data exfiltration
Re:IBM AI ('Bob') Downloads and Executes Malware
on Thursday January 08, 2026 @01:25PM (#46544545)
pretty funny that the text shown users when trying run commands with substitution like $() specifically says they block process substitution in commands, but the code just doesnt block it at all