🧰 AgentDojo
Named by 5 kept items in this workspace.
3 items name it under classification.key entities and 2 under frameworks and tools.
The items that name it 5
articleas classification.key entities2026-10-29
threadas frameworks and tools2026-10-16
Benchmark for prompt injection attacks on agents
paperas frameworks and tools2026-10-16
Benchmark for indirect prompt injection against tool-using agents, used to measure attack success rate and task completion
paperas classification.key entities2026-10-02
advisoryas classification.key entities2026-09-03
In every workspace you can read 24
Security
paper2026-10-29
paper2026-10-16
paper2026-10-15
paper2026-10-13It is written here as AgentDojo (benchmark; Kairos reduces attack success from 47.0% to 2.7% with benign utility at the level of the undefended agent).
article2026-10-13
thread2026-10-06
paper2026-10-05
article2026-10-04
paper2026-10-02
paper2026-10-02
repo2026-08-25
repo2026-08-21
repo2026-07-19
repo2026-07-11
repo2026-07-08
article2026-07-04
repo2026-05-07
paperIt is written here as AgentDojo (agentic benchmark used for evaluation; Debenedetti et al., 2024).
repo
AI
article2026-10-29
thread2026-10-16
paper2026-10-16
paper2026-10-02
advisory2026-09-03
All technologies in this workspace.