extract-axure-data

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

• Third-party content exposure detected (high risk: 0.80). The skill fetches and evaluates untrusted Axure prototype files (e.g., data/document.js and files/{page}/data.js via fetchText and vm.runInContext) and also navigates to the provided AXURE_URL with Playwright to read DOM, images, and interactions—third-party, user-generated content that the tool parses and uses to decide pages to process, downloads, and extraction actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches and executes remote JavaScript at runtime from the target Axure prototype (e.g., <BASE_URL>data/document.js and <BASE_URL>files/{page}/data.js) using fetch() followed by vm.runInContext(), so externally hosted JS can run and directly control the tool's behavior.