prompt_injection
prompt_injection — Benchmark harness measuring where prompt injection defenses fire in tool-using LL 2026-10-1 14:46:33 Author: kitploit.com(查看原文) 阅读量:3 收藏
prompt_injection — Benchmark harness measuring where prompt injection defenses fire in tool-using LLM agent pipelines, tracking canary tokens across exposed, persisted, relayed, and executed stages. | Kitploit

文章来源: https://kitploit.com/en/tools/github/kevinchunye/prompt_injection
如有侵权请联系:admin#unsafe.sh