keyword-research
Warn
Audited by Snyk on Mar 25, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly requires connecting to the Keywords Everywhere MCP server and running tools like "Get Related Keywords", "Get 'People Also Search For' Keywords", "Get Keyword Data", and "Get Domain Keywords" (Steps 3, 3b, and 4 in SKILL.md), which ingest public/untrusted web and competitor keyword data that the agent must read and use to drive clustering, prioritization, and gap analysis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata