Proventra – Open-source prompt injection security for AI agents
Proventra – Open-source prompt injection security for AI agents
We're building Proventra because securing AI agents against prompt injection is a growing challenge, especially for agents interacting with external content (web pages, documents). Existing defenses often fall short or require rejecting potentially valuable content entirely.
Share cardActual performance
Launch Intel predictions
Analyze your own launch →Correct prediction on native model
Similar products
ClawMoat – Open-source runtime security for AI agents (zero deps, <1ms)
ClawMoat – Open-source host-level security for AI agents
DearAgent – Open-source email inboxes for AI agents
AgentPort – Open-source Security Gateway For Agents
Roids – Open Source Steroids for your Agents
Open-source list of top AI agents
ExoAgent – Security kernel for AI agents
Open-Source Data Security Platform
GraphQL Armor – An open source security layer for GraphQL
aligned to the OWASP Agentic Security Initiative (ASI)