Data as of Jul 25, 2026 · Based on 2,718,867 AI responses across 9,511 prompts · See how Parse measures this
AgentDojogithub.comAgentDojo Inspect is a fork of the AgentDojo framework that adds compatibility with the Inspect evaluation framework for testing LLM agents. It provides a dynamic environment to evaluate prompt injection attacks and defenses, including new tasks for mass data exfiltration and remote code execution vulnerabilities.
Parse Score
Sources
arxiv.org shapes more of what AI says about AgentDojo than any other source, at 100% of its citations.
