implement

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

• Third-party content exposure detected (high risk: 0.85). The required workflow includes “If it is a GitHub issue, fetch with gh” and “If the task is a Linear issue, fetch the details and relevant comments,” which at runtime can ingest outsider-authored issue/comment free text into the agent’s LLM context via the GitHub/Linear API responses.