Ideas & society2025 · shared on Hacker News
CaMeL: Defeating Prompt Injections by Design
Explore CaMeL: Defeating Prompt Injections by Design, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Yrd ·
GPT-5
2,063 points2,482 comments
Yrexpository ·
Supabase MCP can leak your entire SQL database
848 points470 comments
Yjacobr1 ·
The Policy Puppetry Attack: Novel bypass for major LLMs
313 points231 comments
Ypvg ·
EchoLeak – 0-Click AI Vulnerability Enabling Data Exfiltration from 365 Copilot
228 points86 comments
Ystuxf ·
From MCP to shell: MCP auth flaws enable RCE in Claude Code, Gemini CLI and more
148 points40 comments
Ynonvibecoding ·
Code execution through email: How I used Claude to hack itself
137 points69 comments
Ynick_wolf ·
Show HN: MCP-Shield – Detect security issues in MCP servers
134 points39 comments
Ythe_mitsuhiko ·
Code Mode: the better way to use MCP
84 points11 comments
Ytomrod ·
CaMeL: Defeating Prompt Injections by Design
71 points16 comments
Yhgaddipa001 ·
Launch HN: Slashy (YC S25) – AI that connects to apps and does tasks
70 points100 comments
Ygronky_ ·
Don't trust AI agents
51 points21 comments
Yedf13 ·
A GitHub Issue Title Compromised 4k Developer Machines
4 points0 comments
Yxnx ·
Defeating Prompt Injections by Design
2 points0 comments
Ytheptip ·
Defeating Prompt Injections by Design
2 points0 comments
Ykyrra ·
Defeating Prompt Injections by Design
1 points0 comments
Yredbell ·
Defeating Prompt Injections by Design
1 points0 comments
Yschmuhblaster ·
Implementing a (Vibed) LLM Coding Agent in Prolog
1 points0 comments