Skip to content
Threat Feed
Subscribe

Product

Decepticon (<= 1.1.16)

1 brief RSS
critical advisory

Decepticon Agent Framework Role-Boundary Forgery via ChatML Special-Token Literals

The Decepticon agent framework fails to sanitize model-specific special-token literals in external reconnaissance data, allowing attackers to forge system-level instructions and execute arbitrary commands in the agent's Kali Linux sandbox.

Decepticon +2 agent-security llm-security prompt-injection rce
1t 1c