Hacker Newsnew | past | comments | ask | show | jobs | submit | manuelnd's submissions login

1. We audited both MCP SDKs – three classes of boundary-crossing vulnerabilities 1 point by manuelnd 81 days ago | past 2. How to Red Team Your AI Agent in 48 Hours – A Practical Methodology 1 point by manuelnd 88 days ago | past 3. The OWASP LLM Top: A Practical Attack Guide (with 122 real attack techniques) 1 point by manuelnd 3 months ago | past 4. Show HN: Open-source taxonomy of 122 AI/LLM attack vectors 1 point by manuelnd 3 months ago | past

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search: