boxlang-core-dev-interceptors

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

• Third-party content exposure detected (high risk: 0.70). The skill clearly ingests and acts on untrusted, user-provided HTTP request content (e.g., onHTTPRequest / onRequestStart events reading cgi.path_info, request payloads or session data), as shown by the A/B routing example that sets event.overridePath from cgi.path_info, so external request data can materially influence interceptor behavior.