ai-site-readiness

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches and reads arbitrary public web pages selected by the user via the advisorsai-check CLI or remote MCP tool.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs runtime installation and execution from a personal GitHub repository (git+https://github.com/manmohm/advisorsai-check), which constitutes a weak/unknown/suspicious operational dependency under the dependency gate.