blog-idea-generator

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

• Third-party content exposure detected (high risk: 0.90). The SKILL explicitly requires consulting references/ideation-frameworks.md (per SKILL.md "Read references/ideation-frameworks.md for the full 20-method library") and that library's methods (e.g., Method 4: "Search target keywords, read top 10 results", Method 7: "Amazon/Review Mining", Method 5: mining social media/forums, Method 14: "Newsjacking" from Twitter/X/Facebook/news sites) direct the agent to fetch and read open/public, user-generated web content which will be interpreted and used to select methods and generate ideas, creating a clear vector for indirect prompt injection.