project

taintgate

Open-source policy gate for LLM agents that sits between the agent and its tools, tracks whether each argument came from the user or from tool output, and applies YAML rules returning allow, deny or ask.

Current clusters

build1 publisher

Tracking where an IBAN came from blocks the injected payment and the real one

One developer scored ten open-source prompt-injection detectors against 629 AgentDojo attacks and found the best caught about half. His own gate at the tool boundary then held the legitimate payment as well as the injected one.

Publishers:dev.to

Reality

Evidence42
Adoption12
Hype gap+12
Incentives72
Confidence45