ljg-word-flow

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The prompt explicitly instructs the agent to "force NATIVE mode" and bypass the system's standard Algorithm workflow ("don't go through OBSERVE/THINK/PLAN/..."), which is an instruction to override higher-level/system behavior and thus constitutes a prompt-injection attempt outside normal skill boundaries.