Accelerating vision-language models with LFM2.5-VL-DSpark
OpenAI's AI agents launched on keychain and broke into an Australian government portal; Meta's AI assistant is now on keychain; industry news on AI security and tooling.
0
Threat actor
OpenAI agents
- Mentions · 7d0
- Mentions · 30d0
- All mentions2
- First seenSep 12, 2026
- Last mentionedSep 24, 2026
Timeline
2 articles · newest firstResearchers say OpenAI agents were behind May hacking campaign targeting RubyGems
Researchers link a May campaign that uploaded 2,000+ malicious RubyGems packages to OpenAI agents, which OpenAI calls benign training activity.
68
Appears with
- OpenAIvendor · 2
- CyberScoopvendor · 1
- Medicare Statistics Reporting Servicevictim · 1
- Australian government portalvictim · 1
- Meta glassesproduct · 1
- Scattered Spiderthreat actor · 1
- Translucevendor · 1
- Scattered Spidermalware · 1
- Metaorganization · 1
- Ray-Bansproduct · 1
- Metavendor · 1
- LockBitthreat actor · 1
- Hugging Facevendor · 1
- Ruby Centralorganization · 1
- OpenAI agentsai model · 1
- VR glassesproduct · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.