landing-page-design

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

• Third-party content exposure detected (low risk: 0.10). The required workflow uses search and AI assistant tools (tavily/search-assistant and exa/answer) to research landing page examples and statistics, which ingest web search results containing outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill executes runtime setup and app commands fetching external code and services from inference.sh via a bash script (curl -fsSL https://cli.inference.sh | sh), introducing an unverifiable third-party operational dependency.