landing-page-design

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

• Third-party content exposure detected (high risk: 0.85). The required workflow includes running belt app run tavily/search-assistant (web-search at runtime), which can fetch and ingest outsider-authored public web page text into the agent’s LLM context for summarization.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill requires the inference.sh "belt" CLI and uses belt app run (e.g., belt app run falai/..., belt app run ...), which at runtime calls inference.sh to execute remote apps/models using the provided prompts (flagging https://inference.sh).