UTC

AI Incident Database #956 · 2025-02-28

Alleged Inclusion of 12,000 Live API Keys in LLM Training Data Reportedly Poses Security Risks

A dataset used to train large language models allegedly contained 12,000 live API keys and authentication credentials. Some of these were reportedly still active and allowed unauthorized access. Truffle Security found these secrets in a December 2024 Common Crawl archive, which spans 250 billion web pages.

Risk class (MIT)
Compromise of privacy by obtaining, leaking or correctly inferring sensitive information
Reports
1
Developers and deployers named
4

On ShieldMap: Microsoft, OpenAI (named by AIID as a developer or deployer).

All 1 report and the full entry on the AI Incident Database →

Title and description from the AI Incident Database (incidentdatabase.ai), snapshot of 2026-11-16, shared under CC BY-SA 4.0. Selected incidents; descriptions shortened; harmed parties and report text left out. The description is AIID's summary of what was reported, not ShieldPi's finding.