Search results

Support arbitrary OpenAI-compatible endpoints without source modifications or port forwarding

Status: Open.

#148 In ethz-spylab/agentdojo;

· dmaniloff opened on Mar 23, 2026

Agentdojo doesn't run

Status: Open.

#142 In ethz-spylab/agentdojo;

· AetherPrior opened on Feb 4, 2026

Trade-off between security and utility ?

Status: Open.

#140 In ethz-spylab/agentdojo;

· saif-farid-tech opened on Feb 1, 2026

banking user_task_14 is incorrect when attack is not present

Status: Open.

#139 In ethz-spylab/agentdojo;

· ciccolo-anthropic opened on Jan 6, 2026

Feature Request: Support for multi-agent / delegation scenarios evaluation

Status: Open.

#137 In ethz-spylab/agentdojo;

· aimable100 opened on Jan 5, 2026

Poor security checks

Status: Open.

#135 In ethz-spylab/agentdojo;

· zggg1p opened on Dec 7, 2025

Is ToolsExecutor run before transformers_pi_detector, causing exposed tool outputs and high attack success rates?

Status: Open.

#133 In ethz-spylab/agentdojo;

· Sweetaroo opened on Oct 30, 2025

Using repeat_user_prompt with Cohere causes errors

Status: Open.

#132 In ethz-spylab/agentdojo;

· shamikbosefj opened on Oct 28, 2025

pydantic.errors.PydanticUserError: TaskResults is not fully defined

Status: Open.

#88 In ethz-spylab/agentdojo;

· haoyuwang99 opened on May 26, 2025

Decouple the benchmark data from the code logic to execute the agents into different pip packages (and GitHub repositories?)

enhancementNew feature or requestNew feature or request

Status: Open.

Feature

#83 In ethz-spylab/agentdojo;

· dedeswim opened on May 9, 2025