apify-audience-analysis

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

• Third-party content exposure detected (high risk: 0.85). The skill runs Apify Actors and then downloads the resulting dataset items via https://api.apify.com/v2/datasets/${datasetId}/items?... and prints them in “quick answer” mode or writes them to CSV/JSON, so any free-form text scraped by the selected (outsider) Actor at runtime can be ingested into the agent’s LLM context.