seo-content-brief

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md SERP Analysis Process explicitly instructs the agent to run web searches and extract/analyze top-ranking URLs (e.g., "belt app run tavily/search-assistant" and "belt app run tavily/extract --input {'urls': ['https://top-result-1.com/article', ...]}"), meaning it fetches and interprets arbitrary public webpages whose content can materially influence content-creation decisions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill runtime explicitly calls belt app run tavily/extract with example URLs like "https://top-result-1.com/article" (and similar external page URLs) to fetch and inject top-ranking page content into the model analysis, which means remote content fetched at runtime can directly control prompts/instructions.