product-inspiration

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 fetch and analyze public app pages and URLs (e.g., Notion, Linear, Stripe) and then uses those findings to drive implementation, comparison, and selection decisions, meaning untrusted third‑party content can influence agent actions.