Security●●Solid
ClawGuard – Detect 42 prompt injection patterns in <10ms
42 prompt injection patterns detected in under 10ms with zero dependencies.
Niche GemShip It
joergmichno
233mo ago
Python CLI to detect Agentjacking injection attacks in Sentry error events
Scans Sentry events for Agentjacking before your AI agent reads them.
Teams using AI coding agents with Sentry error tracking
PromptInject · Garak · LLM Guard
42 prompt injection patterns detected in under 10ms with zero dependencies.
Dynamic LLM sandbox analysis detects injections that static pattern matching tools miss.
Yet another LLM ops layer when LangSmith, Helicone, and Braintrust already exist.
Another guardrail API competing with Lakera, but claims sub-30ms latency.
Outperforms existing open-source injection detectors on ProtectAI and Qualifire benchmarks.
Beats ProtectAI by 19% accuracy and runs 9x smaller on CPU.