Frequency
2
occurrences
First Seen
January 13, 2026
Last Seen
January 13, 2026
Exploited in Wild
—
Ransomware Use
—
Public Exploits
—
Attack Vector
—
Vulnerability Overview
Exploitation Activity
Exploitation Intelligence
Vulnerabilities have been identified in popular AI and ML Python libraries used in Hugging Face models, allowing remote attackers to embed malicious code in metadata. This code executes automatically when a file with the poisoned metadata is loaded. The affected libraries include NeMo, Uni2TS, and F...
Public Exploits
Checking GitHub for proof-of-concept code…
