Repo

prompt-injection-defense

Python prompt-injection defense for LLM agents: default-deny policy broker, labeled ingest, quarantine extract, detectors, and offline ASR/FPR eval

Built with

Pythonagent-securityai-agentsllm-securityprompt-injection

pythonsecurity

Comments · 0

No comments yet. Tried it? Tell Kirill what worked, what didn't, or what you'd want next.

See what other members are building and what each project is looking for.