medusa-testing
Warn
Audited by Snyk on Mar 31, 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 live docs" via web-search (e.g., "Web-search medusajs v2 jest test workflow 2026") and to fetch https://docs.medusajs.com/resources/medusa-testing, meaning the agent will ingest public third‑party web content (including arbitrary web-search results) that can materially change test configuration and behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata