design-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 explicitly directs the agent to use web_search and web_fetch to gather and analyze competitor websites and industry trends (e.g., "Use
web_searchfor industry trends and competitor analysis" and "Useweb_fetchto analyze competitor websites and apps"), which means it ingests open/public third‑party content (untrusted public websites/reviews) that the agent is expected to read and interpret.
Audit Metadata