blog-calendar
Warn
Audited by Snyk on Jun 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow includes “Research seasonal opportunities” using WebSearch to check Google Trends and validate timing of trends before scheduling, which can ingest outsider-authored public web content (search results/pages) as readable text into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata