data-enrichment

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). The skill explicitly directs the agent to fetch and use external web content—SKILL.md's "Handling missing data" tells the agent to "use built-in WebSearch and WebFetch tools to find additional information" (and the main workflow consumes structured JSON from external stableenrich.dev APIs), so the agent will read untrusted third-party content that can materially influence subsequent tool calls and decisions.