add-linear

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

• Third-party content exposure detected (high risk: 0.90). The skill forwards and ingests all Linear issue comments via webhook-driven channel integration (see SKILL.md "Credentials" webhook setup and "typical-use: Webhook-driven" / the catch-all onNewMessage handler), so untrusted user-generated comments from Linear could be read and directly influence the agent's actions.