seo-content-brief

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow uses belt app run tavily/search-assistant / exa/search to fetch and analyze top-ranking web pages (public web content) and then feeds extracted text from those outsider-authored pages into the agent/LLM context for SERP analysis.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill calls the inference.sh CLI ("belt") to run remote apps (e.g., "belt app run tavily/search-assistant" / "belt app run exa/search") which execute remote code and control the agent's prompts/outputs at runtime via https://inference.sh.