keyword-research
Warn
Audited by Snyk on Feb 16, 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's "Expansion Sources" explicitly includes fetching content from competitor URLs, forums, and other public auto-suggest/People Also Ask sources, meaning the agent is expected to ingest and interpret untrusted, user-generated or public web content that could carry indirect prompt injection.
Audit Metadata