local-keyword-research
Warn
Audited by Snyk on Mar 19, 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.md explicitly instructs the agent to fetch and scrape open web sources (Step 2/Step 2.5: "pull" data from Semrush/Ahrefs/DataForSEO, use Google Autocomplete/People Also Ask/SERP API, and "scrape their service pages" and SERP results), meaning the agent will ingest untrusted third-party web content that can materially influence keyword decisions and subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata