linear-skill

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

• Third-party content exposure detected (high risk: 0.80). The skill makes GraphQL requests to the public Linear API (https://api.linear.app/graphql) and explicitly fetches and returns user-generated issue fields and comments (see cmd_issue, cmd_my_issues, cmd_search, etc.), which the agent is expected to read as part of normal workflow and could therefore carry instructions that influence subsequent tool use or decisions.