awesome-marketing-skills-library

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly routes research and imagery through external MCP servers (tavily, firecrawl, and stock-images/PEXELS) via functions like researchLocation and fetchContextualImage and the example generatePremiumBrochure workflow, meaning the agent fetches and ingests open/web user-generated third‑party content that directly influences generation and tool actions.