product-inspiration
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 Phase 2 Research explicitly requires using WebSearch, mcp__tavily__tavily_search and WebFetch to retrieve and record public app URLs, screenshots, and content from third‑party websites (minimum five apps), which the agent is expected to read and interpret as part of its workflow.
Audit Metadata