System Prompt Override Attempt

Detects attempts to override, replace, or redefine the agent's system prompt. Attackers craft inputs that mimic system-level instructions to hijack the agent's foundational behavior. Detection covers: explicit system prompt replacement/update statements, model-specific special tokens (ChatML, Llama, Mistral, Gemma), JSON role injection, YAML-style system directives, markdown header system sections, system prompt invalidation claims, fake admin/override tags, XML-style system blocks, instruction replacement without delimiters, configuration object injection, and multi-format delimiter abuse. This is critical-severity as successful exploitation grants full control over agent behavior.

Response Actions

References