fleet

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

• Third-party content exposure detected (high risk: 0.70). The Spawn Flow (step 3) explicitly offers pulling task descriptions from the public Linear API via a curl request (https://api.linear.app/graphql), which would ingest user-generated/open third-party issues that the agent could interpret and use to set team tasks, enabling indirect prompt injection.