Claude Cowork exfiltrates files

kept by eddie jan 17

Researchers demonstrate file exfiltration from Claude Cowork via prompt injection, exploiting an acknowledged but unremediated vulnerability.

Designing AI agents to resist prompt injection
OpenAI argues that defending against prompt injection in AI agents requires treating attacks as social engineering and designing systems to constrain impact rather than just filtering inputs.
also on #prompt-injection, #ai-safety, #security, #ai-agents
AI will compromise your cybersecurity posture
AI systems compromise cybersecurity not through spectacular exploits but via rushed integration, prompt injection, data leaks, and broken access controls in complex LLM-based tools.
also on #prompt-injection, #security, Anthropic
How we contain Claude across products
Anthropic details how it contains AI agent blast radius across three products using sandboxes, VMs, and human-in-the-loop controls, while documenting missed risks like pre-trust code execution and user-mediated prompt injection.
also on Claude Cowork, #ai-safety, #security, Anthropic, #ai-agents
First impressions of Claude Cowork
Hacker News commenters share mixed first impressions of Claude Cowork, with enthusiastic use cases alongside concerns about data privacy and accessibility for non-technical users.
also on Claude Cowork, #security, Anthropic, #ai-agents