nodel-recipes

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

• Third-party content exposure detected (high risk: 0.90). The skill includes multiple runtime HTTP fetch patterns (get_url) that call user-configurable endpoints (e.g., BASE_URL built from param_ipAddress in references/patterns.md and the HTTP examples in references/toolkit-api.md), and it parses/uses those responses (json_decode, dynamic action/event creation such as discover_sources), so it clearly ingests untrusted/third-party content that the agent will read and act on.