linear

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow uses the Linear GraphQL API to fetch issue/comment/document text (e.g., cmd_get_issue returns comments { body user { name } } and cmd_get_document returns content), and those fields can include prose authored by other Linear users (outsider-authored free text) that is then placed into the agent’s LLM context via the tool output.