context-engineering-collection

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

• Third-party content exposure detected (high risk: 0.90). The repository's README and SKILL.md explicitly show runtime flows that fetch public URLs (e.g., the "Using Individual Skills" curl to raw.githubusercontent.com) and include examples that monitor public X accounts (the x-to-book-system), so agents using these skills are expected to ingest untrusted, user-generated web/social-media content that can influence subsequent actions.