adaptive-learning-playbook

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

• Third-party content exposure detected (high risk: 0.90). The skill's core workflow (SKILL.md "Collection Architecture" and "Competitive Intelligence" sections) and the extended guidance (references/extended-playbook.md "AI-Augmented Workflow" which explicitly says "Crawl competitor sites" and "Feed trend data to Claude") direct the agent to gather and synthesize open/public third-party sources (GitHub Trending, Hacker News, ProductHunt, social media, websites, job boards, regulatory filings), meaning untrusted user-generated content would be read and used to drive decisions and actions.