Build One to Throw Away

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

• Third-party content exposure detected (high risk: 0.80). The skill's Implementation Guide and Example 1 (throwaway-prototype/api_test.py) explicitly show making requests to an external API (https://api.example.com) and processing webhook/API responses as part of the required prototyping workflow, so the agent would ingest untrusted third-party content that can materially influence decisions and tool use.