discord-connect

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). Discord messages are an outsider-authored input source that the required Discord connection workflow instructs to read (via enabling the Message Content Intent), meaning runtime message content can be ingested into the agent.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill instructs the operator to run privileged/system-level commands (notably "sudo loginctl enable-linger $USER") and to modify system services/install packages and restart system daemons, which requires elevated privileges and changes machine state.