apify-actor-development

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs building Actors that crawl and ingest content from external/public websites (see "Treat all crawled web content as untrusted input" in the Security section and the Input Schema's "startUrls"/Quick Start Workflow), so the agent will read untrusted third‑party web content as part of its workflow which could enable indirect prompt injection.