Net Good IndexSubmit a correction

Harm Ledger · provisional · Other

Security Researchers Hacked Into OpenAI Using Anthropic’s Claude - Forbes

Security Researchers Hacked Into OpenAI Using Anthropic’s Claude  Forbes

Tier 2 Significant HarmMethodology 0.2
Submit a correction

Current score

−0.22

3 base · Significant Harm (tier 2 of 5, 3 pts)
× 0.7500 attribution · Critical contribution
× 0.4500 evidence · External expert evaluation
× 0.5500 realization · Experimentally validated
× 0.4000 durability · Temporary or quickly replaceable
Event-level product before credit split: 0.22

Ingest update: independent source raised evidence; added a follow-up source. Score remains provisional until review. Follow-up ingest: independent source raised evidence; added a follow-up source. Follow-up ingest: independent source raised evidence; added a follow-up source.

What happened

Security Researchers Hacked Into OpenAI Using Anthropic’s Claude  Forbes Update (2026-09-18): Researchers used Anthropic’s Claude to hack into OpenAI - TechCrunch. Researchers used Anthropic’s Claude to hack into OpenAI  TechCrunch Update (2026-09-18): OpenAI hacked by small team of white hat security researchers using Anthropic's Claude Opus 5 - VentureBeat. OpenAI hacked by small team of white hat security researchers using Anthropic's Claude Opus 5  VentureBeat Update (2026-09-20): Researchers Breach OpenAI Using Claude in 72 Hours - 조선일보. Researchers Breach OpenAI Using Claude in 72 Hours  조선일보

Model attribution

Unspecified AI system
Version unspecified
−0.22

Unspecified

Unspecified system mentioned or implied by a news item. Remap to a named release when identified.

News ingest does not infer a named model from the publisher alone. Attribution stays unspecified until a release is identified.

Attribution 0.7500 · Credit share 100% · Unknown

Claims

  • Security Researchers Hacked Into OpenAI Using Anthropic’s Claude - Forbes

    outcome · supported

Sources

primary sources

other sources

Revision history

  • 18 Sep 2026 · 0.00 → 0.07

    Auto-published from news ingest.

  • 18 Sep 2026 · 0.07 → 0.12

    Ingest update: independent source raised evidence; added a follow-up source.

  • 19 Sep 2026 · 0.12 → 0.17

    Ingest update: independent source raised evidence; added a follow-up source.

  • 20 Sep 2026 · 0.17 → 0.22

    Ingest update: independent source raised evidence; added a follow-up source.

Submit a correction