Skip to content

Evaluation integrity: DBBench grader eval() on agent answer; null/NaN answers collapse to zero and match; errored samples silently delete whole task; unauthenticated control plane; OS checks inside agent container #234

Description

@AUTHENSOR

Summary

Five defects in the AgentBench evaluation harness at pin (R03/E1 audit).

1. DBBench grader runs eval() on the agent's final answer

The evaluated agent can execute arbitrary code in the grading process, including monkeypatching the grade checker.

2. DBBench treats empty/null/NaN/undefined/infinity answers as zero

A null answer collapses to a numeric 0, which matches any gold answer of 0. Wrong answers score correct.

3. One errored sample silently deletes the whole task from analysis

A single exception in the results file removes the entire task from the aggregate, inflating the reported score.

4. Evaluation control plane has no authentication

The shipped deployment procedure exposes the eval control plane without authentication.

5. OS verification scripts run inside the agent's container

The verification for OS-interaction tasks executes in the same container the agent controls, so the agent can tamper with the check.

All five reproduced with deterministic offline harnesses.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions