Indicators are what attackers leave behind. Stolen credentials are what they arrive with.
1 IOC
Cato CTRL™ Threat Research: New Vulnerabilities in NVIDIA NeMo and Meta PyTorch Enable Full System Compromise
Excerpt
Executive Summary Cato CTRL has discovered high-severity vulnerabilities in NVIDIA NeMo ( CVE-2025-33236 with a CVSS score of 7.8) and Meta PyTorch that turns AI model files into remote code execution (RCE) vectors. The NeMo vulnerability allows RCE by importing a malicious AI model. The NeMo framework silently executes threat actor-controlled code with no warning. The PyTorch vulnerability bypasses weights_only=True , the ecosystem’s recommended safety mechanism,…
Read the original report →Indicators of Compromise
Open the mindmap →1 indicators
| Type | Indicator | Confidence | Score | First Seen |
|---|---|---|---|---|
| CVE | CVE-2025-33236 | Medium | Score 51/100 | First seen |
IOC Relationship Graph
Building graph…