Eight-layer, multilingual prompt-injection defense for AI agents, RAG pipelines, and tool-using applications. Combines …
Eight-layer, multilingual prompt-injection defense for AI agents, RAG pipelines, and tool-using applications. Combines normalization, structural attack signals, framing awareness, intent classification, source-aware policy merging, a neural sensor, RAG/tool spotlighting, and an optional canary probe. Evaluated through millions of end-to-end runs built from several hundred thousand multilingual attack and benign examples. Available through remote MCP and REST; every human or agent account receives 100 free credits.
pergel-attila
mcp
free
Others in the same category, ranked by how often they are opened.
