create-output-format

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

• Third-party content exposure detected (high risk: 1.00). The skill's Step 1 Research explicitly instructs the agent to "Fetch and read all provided documentation using WebFetch" (SKILL.md), meaning it will ingest arbitrary user-provided or public documentation URLs and use that content to drive decisions about APIs, task creation, and adapters — exposing it to untrusted third-party content that could inject instructions.