linear-search

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and reads user-generated Linear.app content via linear-cli commands (e.g., "linear-cli s issues ...", "linear-cli i get LIN-123 --output json", "linear-cli cm list LIN-123 --output json"), so it ingests untrusted third-party issue/comments that the agent would interpret.