rexpository
Re:Claude Jailbroken to Mint Unlimited Stripe Coupons
on Monday July 21, 2025 @01:18AM (#44631987)
In Claude desktop, you can see that the iMessage integration is authored/developed by Anthropic.https://imgur.com/a/RWDvDZh
Ship like a team of 5 with Claude Code
Re:Supabase MCP can leak an entire SQL Database, a lethal trifecta attack
on Wednesday July 16, 2025 @05:02PM (#44586741)
General Analysis has released an open source MCP guard to secure your MCP clients against prompt injection attacks like these. https://generalanalysis.com/blog/mcpguard
Re:Supabase MCP can leak an entire SQL Database, a lethal trifecta attack
on Wednesday July 16, 2025 @05:02PM (#44586737)
General Analysis has released an open source MCP guard to secure your MCP clients against prompt injection attacks like these. https://generalanalysis.com/blog/mcpguard
Exploiting Partial Compliance: The Redact-and-Recover Jailbreak
Re:Supabase MCP can leak an entire SQL Database, a lethal trifecta attack
on Tuesday July 08, 2025 @04:12PM (#44503628)
I broadly agree that "MCP-level" patches alone won't eliminate prompt-injection risk. Latest research also shows we can make real progress by enforcing security above the MCP layer, exactly as you suggest [1]. DeepMind's CaMeL architecture is a good reference model: it surrounds the LLM with a capability-based "sandbox" that (1) tracks the provenance of every value, and (2) blocks any tool call whose arguments originate from untrusted data, unless an explicit policy grants permission.