seo-ai-optimizer

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

• Third-party content exposure detected (low risk: 0.10). The workflow reads local project source files and executes web searches for SEO best practices, but does not ingest outsider-authored free text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill contains instructions for installing a dependent skill (website-agent-readiness) via an external repository locator (github:luongnv89/skills:skills/website-agent-readiness) which is fetched at runtime during preflight, representing a common unofficial operational dependency.