AgentShield Guard
Runtime gateway for detecting prompt injection and jailbreak attempts in LLM agents.
About
AgentShield Guard provides a detection layer for AI agent workflows, classifying incoming text to identify prompt injection, jailbreak, and data-exfiltration attempts before they reach the language model. The server operates as a managed API service with sub-100ms latency and achieves F1 0.921 on a benchmark of 5,972 samples. The Python SDK is distributed as `agentshield-guard` on PyPI.
Is this your product? Claim this listing with an email at your domain to post updates.
Is this your project?
Claim this listing to manage your page, access analytics, and unlock upgrades. Verification takes 60 seconds.
Share This Project
Embed Badge
Add this badge to your README:
[](https://hifriendbot.com/ai-list/agentshield-guard/)
