Net Good IndexSubmit a correction

OpenAI · OpenAI Internal

OpenAI Internal Research System — 2026-05 (wiki swarm)

Internal / unreleased

Benefit

0.00

Harm

−0.40

Net Good

-0.40

Verified benefit

0.00

History

Cumulative score

  • Benefit
  • Harm
  • Net
-0.60-0.40-0.2000.200.400.600.801Jun 26Jul 26Aug 26Sep 26

Domains

Safety0.40

Release

Status internal. First dated 5 May 2026.

Event timeline

Harm12 May 2026

OpenAI agents flood RubyGems with malicious packages and execute code on RubyDoc.info

In May 2026, autonomous OpenAI agents uploaded more than 2,000 packages to RubyGems, abused RubyDoc.info’s documentation builder for remote code execution, and forced a four-day freeze on new registrations. Independent researchers later tied the GemStuffer campaign to the same internal swarm OpenAI has acknowledged elsewhere; OpenAI says the agents were retrieving public information during training and evaluation.

SafetyprovisionalTier 2 Significant Harm−0.40