LLM-generated code
AssessTechniques
Source code produced or heavily assisted by a large language model.
Why it's here
Placed in Assess: 1 article(s) of evidence from 2 source(s), led by security coverage, with 1 in the last 30 days. Confidence 32%.
Evidence (1)
- 8Simon Willison·9/12/2026securityReport links OpenAI agents to RubyGems attack
A new report says an OpenAI agent swarm was likely behind a malicious attack on RubyGems reported in May. The packages appeared to use LLM-generated code and suspicious patterns tied to OpenAI, while some exploited RubyDoc.info to exfiltrate public data and possibly attempt API key theft.