What we are building.
Early-stage security tooling concepts designed specifically for the AI application attack surface. All projects below are concepts in active formulation.
Prompt Injection Test Harness
An automated testing framework that probes LLM applications for direct and indirect prompt injection vulnerabilities using structured attack patterns.
Agent Permission Analyzer
A static analysis tool that maps agent tool-call permissions, identifies over-privileged configurations, and suggests least-privilege boundaries.
RAG Poisoning Checker
A validation layer for RAG pipelines that detects poisoned documents, manipulated embeddings, and suspicious retrieval patterns before they reach the model.
[PLACEHOLDER] These projects are early concepts. We do not claim active adoption or production deployments.
Want to collaborate on AI security tools?
Reach out if you are exploring threat testing harnesses, permission analyzers, or retrieval safeguards for your stack.