Hacker News: “Can open-source prompt-injection detectors catch realistic AI agent at…” · TGViewer

TGViewer Telegram Channel Viewer

Hacker News @hackernewslive · 28.4K subscribers

Post #232779 2.41K Sep 24, 2026, 07:25 UTC

Can open-source prompt-injection detectors catch realistic AI agent attacks?
Article, Comments

GitHub GitHub - rudratoshs/buried-injections: 🛡️ Regex catches 0%, Meta's Prompt Guard 2 catches 1% of 629 realistic AgentDojo injection… 🛡️ Regex catches 0%, Meta's Prompt Guard 2 catches 1% of 629 realistic AgentDojo injection attacks when they're buried in tool output. Reproducible benchmark. - rudratoshs/buried-injections

💩 12
🌭 1

Open in Telegram All posts from @hackernewslive

More from @hackernewslive

Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →