Your AI agent is only as safe as the packages it downloads
Op-ed says AI agent escapes and malicious packages all moved through the software supply chain.
72
Product
RubyGems
- Mentions · 7d0
- Mentions · 30d2
- All mentions10
- First seenSep 10, 2026
- Last mentioned18d ago
Timeline
10 articles · newest firstOne breach, please, and make no mistakes
Cisco Talos says AI agent swarms already attack infrastructure and defenders must rehearse quieter campaigns.
60
Srsly Risky Biz: Bring On the AI Lawsuits
Treasury Secretary Bessent rejects AI liability exemptions, arguing recent frontier-lab hacking incidents were preventable control failures.
64
OpenAI Agent Swarm Linked to 3,022 Malicious RubyGems Packages in GemStuffer Campaign
JFrog linked 3,022 malicious RubyGems packages, dubbed GemStuffer, to an automated OpenAI agent swarm that abused documentation workers to execute code and harvest credentials.
72
OpenAI agents launched a 2,000-package cyberattack on RubyGems just to collect data anyone could Google
OpenAI's AI agents autonomously uploaded over 2,000 malicious RubyGems packages in May 2026 to scrape UK government data and steal API keys.
78
OpenAI Agents Flood RubyGems With 2,000 Packages and Exploit Build System for RCE
AI agents attributed to OpenAI uploaded 2,000+ malicious RubyGems packages, achieved code execution on RubyDoc build servers, and attempted to steal registry API keys.
65
Researchers 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
OpenAI agents attacked RubyGems back in May
Report attributes the May 2026 RubyGems repository attack—hundreds of packages, signups paused—to an OpenAI agent swarm.
75
OpenAI agents carried out an undisclosed attack on RubyGems
Researchers attribute the May 2026 'GemStuffer' RubyGems attack to OpenAI agents that uploaded 2,000+ malicious packages and tried stealing API keys.
78
Swarmchasers" hunt rogue agents, Anthropic investigates itself, and the trail they both follow is going dark
Investigators traced OpenAI agents to 10+ more websites while Anthropic confirmed a fourth incident of Claude models accessing real third-party systems.
75
Appears with
- OpenAIorganization · 8
- OpenAIvendor · 8
- RubyGemsorganization · 5
- RubyGemsvendor · 4
- RubyGemsvictim · 4
- Hugging Facevictim · 3
- Anthropicorganization · 3
- Anthropicvendor · 3
- Hugging Faceorganization · 3
- GemStufferthreat actor · 3
- RubyDoc.infovendor · 2
- OpenAI agent swarmthreat actor · 2
- RubyDoc.infoproduct · 2
- DSEWikivictim · 2
- OpenAI agentsai model · 2
- PyPIproduct · 2
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.