apify-sdk-integration

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly runs Apify Actors on arbitrary startUrls (seen in the JS/Python examples and REST POST) and then retrieves dataset items and key-value-store records (e.g., client.dataset(...).listItems(), keyValueStore.getRecord('OUTPUT')), so the skill ingests untrusted public web content that the agent would read and could materially influence downstream actions.