The Bot Left a Fingerprint: Detecting and Attributing LLM-Generated Passwords
ID: f19c0d65-f89a-55fa-8d71-ddbbb94db9cb
STIX ID: report--f19c0d65-f89a-55fa-8d71-ddbbb94db9cb
Feed Name: Security Boulevard
Threat Score
This GitGuardian blog post analyzes how LLMs produce predictable, biased passwords, builds Markov-chain models to detect and attribute LLM-generated secrets, and reports identifying ~28,000 suspected LLM-generated passwords in GitHub commits (from a 34M-password sample), highlighting risks of AI-generated and agent-hardcoded secrets and recommending vaults, agent guardrails, and scanning tools.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.