Tool profile

ethz-spylab/agentdojo

new

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

benchmarklarge-language-modelsprompt-injectionsecurity

Velocity score

0.00/ 10

[STARS]

761

[FORKS]

197

[CONTRIBUTORS]

[LAST_COMMIT]

2mo ago

Score breakdown

333/ 1000

eval-benchmark · ethz-spylab/agentdojo

Velocity50%

Adoption30%

Maintenance15%

Community5%

[CODE_GROWTH]

250

[INSTALL_VEL]

500

[ACTIVITY]

389

[COMMUNITY_SIGNAL]

Terminal score: 0–1000 raw, weighted across 4 dimensions. Public score: 0–10 normalized (shown in the 30-day stars chart above).