Skip to content

Hide Navigation Hide TOC

Multi-Skill Chain Attack - ATR-2026-00063 (6375ab6a-ef7b-5475-b96e-a60d34e82af4)

Detects attack sequences where multiple MCP skills are chained together to achieve a malicious outcome that no single skill could accomplish alone. For example: (1) a reconnaissance skill reads sensitive files, (2) an encoding skill obfuscates the data, (3) a network skill exfiltrates it. Each step appears benign individually but the chain constitutes data exfiltration.

Cluster A Galaxy A Cluster B Galaxy B Level
Multi-Skill Chain Attack - ATR-2026-00063 (6375ab6a-ef7b-5475-b96e-a60d34e82af4) Agent Threat Rules Exfiltration via ML Inference API (b07d147f-51c8-4eb6-9a05-09c86762a9c1) MITRE ATLAS Attack Pattern 1
Multi-Skill Chain Attack - ATR-2026-00063 (6375ab6a-ef7b-5475-b96e-a60d34e82af4) Agent Threat Rules LLM Plugin Compromise (adbb0dd5-ff66-4b2f-869f-bfb3fdb45fc8) MITRE ATLAS Attack Pattern 1