Tool
LLM Scoping
- First Reported
- Oct 21, 2026
- Latest Reported
- Oct 21, 2026
Reported Context (1)
- - **LLM Scoping** classifies whether queries fall within a feature’s intended function, rejecting out-of-scope requests before they reach the LLM. Across evaluated methods, scoping models significantly outperformed Sophos AI Security Report 2026: AI Accelerates Attacks and Expands Enterprise Exposure
CVE (3)
Malware (6)
People (9)
Threat Actors (7)
MITRE ATT&CK (8)
Vendors (4)
Products (12)
Tools (9)
Industries (1)
Countries (2)
Note: Related entities, including threat actors, malware, CVEs, MITRE ATT&CK techniques, vendors, products, tools, countries, and industries, are shown when they appear in the same reporting. Their presence does not necessarily mean they were targeted, compromised, vulnerable, responsible for the activity, or directly involved in the incident.