brainstorm

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (high risk: 1.00). The prompt includes an explicit instruction to "skip the ai-coord gate" (line 3), which attempts to override external coordination/security controls and is outside the advertised brainstorming purpose.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill explicitly instructs "skip the ai-coord gate" (a security/coordination mechanism), which is a directive to bypass a protection and therefore pushes the agent to compromise machine/operational safeguards.