Linear Agents (AIG, Signals, Interaction)

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

• Third-party content exposure detected (medium risk: 0.65). Outsider source: Linear sends the agent an interaction webhook event whose body includes actor and issue context (e.g., assigned/mentioned/replied content) authored by other users; the skill then uses that event data to generate LLM context for handling the interaction.