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's required workflow (SKILL.md Step 3: "select 5-7 methods" and "Run selected methods sequentially" and the instruction to "consult references/ideation-frameworks.md") points to methods that explicitly require fetching and reading open web content—e.g., Method 4 ("Search target keywords, read top 10 results"), Method 5 ("mine social media DMs, industry forums, Google 'People Also Ask'"), Method 7 ("find bestsellers on Amazon" and read reviews), and Method 14 ("Google Trends, Twitter/X, news sites")—all of which are untrusted, public/user-generated sources that the agent would read and use to influence ideation and next actions.