super-skills

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly describes fetching and scraping public web content and registries—e.g., "Multi-platform scraping → browser_automation", the e‑commerce example "Scrape product data from multiple platforms daily", and references to browsing https://skills.sh/ and polling GitHub issues—meaning the agent would ingest untrusted, user-generated third‑party content.