agentic-seo-skill

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

• Third-party content exposure detected (low risk: 0.10). The required workflow involves analyzing arbitrary target websites using URLs provided by the user via web fetching and crawling scripts, which constitutes active search/fetch of outsider-controlled web pages (low risk).

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs users to run remote installation scripts via curl and git clone from a personal GitHub repository, establishing an unverifiable runtime external dependency under weak/unknown provenance.