gtm-meta-skill

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs agents to fetch and scrape public third-party sites (e.g., "Known-source extraction" and direct extraction examples in finding-companies-and-contacts.md, Apify actor calls in provider-playbooks/apify.md, Cloudflare/firecrawl/parallel_extract and google_search examples) and to read and synthesize that untrusted, user-generated web content as part of enrichment/research flows (enriching-and-researching.md), which can materially influence tool use and subsequent actions.