seo-rankings

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

• Third-party content exposure detected (low risk: 0.10). The workflow reads search engine ranking results and snippets from Google via an MCP tool, which includes outsider-authored web page titles and snippets.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the installation of external plugins and connection to remote MCP servers from third-party sources without verified provenance, representing a weak/unknown operational dependency.