write-blog
Warn
Audited by Snyk on Feb 14, 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 instructs the agent to analyze live SERP results with "Use WebSearch to check what currently ranks" (Step 1C) and to query Unsplash's public API for images, both of which fetch and require the agent to read/interpret open, third-party/user-generated web content.
Audit Metadata