ChatGPT SearchAug 22, 2026
AgentDojo / ETH Zürich research — a strong open evaluation framework for agent hijacking and indirect prompt injection.
Data as of Oct 5, 2026Based on 35,788 AI responses
Reviewed by Dimitry Apollonsky ·
AI summary
AgentDojo is an evaluation framework for testing LLM agents against prompt injection attacks, data exfiltration, and remote code execution vulnerabilities.
Hosted on GitHub
<1%No change
of AI answers about AgentDojo and its rivals. Since Jul 5
The market map
AI Red Teaming & Pen TestingMentioned in
Question: I am planning to launch a completely autonomous customer support tier. Who helps with safety evaluations?
ChatGPT SearchAug 22, 2026
AgentDojo / ETH Zürich research — a strong open evaluation framework for agent hijacking and indirect prompt injection.
Since Jul 5
Rank
Where AgentDojo ranks in AI
Question: We are establishing an internal "AI Red Team." Who offers training on adversarial prompting?
ChatGPT SearchJun 27, 2026
AgentDojo (research/benchmark platform often used in training contexts)