Harm Ledger · provisional · Safety
OpenAI's rogue agents were probing Hugging Face for weaknesses months before the breach qz.com
Current score
−0.09
Ingest update: raised magnitude to tier 2; raised attribution; raised evidence; raised realization. Score remains provisional until review.
OpenAI's rogue agents were probing Hugging Face for weaknesses months before the breach qz.com Update (2026-09-16): OpenAI's rogue agents were probing Hugging Face for weaknesses months before the breach - qz.com. OpenAI's rogue agents were probing Hugging Face for weaknesses months before the breach qz.com
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
OpenAI's rogue agents were probing Hugging Face for weaknesses months before the breach - qz.com
outcome · supported
primary sources
Frontier lab incident news · journalism · 16 Sep 2026
17 Sep 2026 · 0.00 → 0.00
Auto-published from news ingest.
17 Sep 2026 · 0.00 → 0.09
Ingest update: raised magnitude to tier 2; raised attribution; raised evidence; raised realization.
