python-json-parsing

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs parsing and scraping arbitrary public web content (see "Web Scraping: Handling Non-Standard JSON" and the chompjs example for extracting hidden web data from tags) and thus expects the agent to ingest untrusted third‑party page content that could influence processing or behavior.