case-study-writing

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 (public web research) which fetches outsider-authored web page text/answers and feeds it into the agent’s LLM context for case-study writing.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires the inference.sh CLI (https://inference.sh) and uses belt app run (e.g., infsh/python-executor and tavily/search-assistant) which submits code/prompts to a remote service that executes the provided Python code and controls prompts at runtime, creating a clear external execution/control dependency.