condition-based-waiting

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow and reference code explicitly make and handle HTTP requests to arbitrary APIs and endpoints (see SKILL.md Step 5 "Parse Retry-After header" and references/implementation-patterns.md: RateLimitedClient.request, check_http, and retry_with_backoff examples), so untrusted third-party response headers/bodies could be ingested and materially influence retries, waits, and control flow.