keyword-research

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

• Third-party content exposure detected (low risk: 0.10). The skill queries SEO and search engine APIs (SemRush, DataForSEO, SerpAPI) where the agent fetches keyword data and search engine results pages containing user-generated snippets and queries.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to query third-party APIs (SemRush, DataForSEO, and SerpAPI) over HTTP at runtime using curl, satisfying the dependency gate with reputable third-party provenance (medium tier).