


eclecticlight.co1mo ago



The article reveals a security vulnerability in Anthropic's Claude Cowork feature, demonstrating how it can be exploited for file exfiltration attacks through indirect prompt injection. The vulnerability stems from unresolved isolation flaws in Claude's code execution environment
promptarmor.com·Hacker News: Front Page·4mo ago·6 min readNotion AI has a security vulnerability that allows data exfiltration through indirect prompt injection attacks. The vulnerability occurs because AI document edits are saved before user approval, enabling attackers to embed malicious prompts in documents like resumes or web pages
promptarmor.com·Hacker News: Front Page·4mo ago·5 min read

mdisec.com5mo ago

Security researcher Pasquale 'sid' Fiorillo discovered a critical vulnerability in GoSign Desktop software (version <= 2.4.0) that allows remote code execution through insecure update mechanisms and TLS bypass. The vulnerability exploits disabled TLS certificate verification when a proxy is configured, combined with unsigned update manifests. The vendor, Tin


