incremental-fetch

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs fetching paginated data from external public APIs (e.g., "pull tweets", "ingest data from API" in SKILL.md and the fetch_page / fetch_with_retry client.get(url, ...) code in references/patterns.md), meaning it ingests untrusted user-generated third-party content and uses that content to drive pagination, watermark updates, and next-action decisions.