extract-site
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external URLs to generate design specifications and update wiki reports. * Ingestion points: HTML and text content scraped from user-provided URLs during the extraction workflow. * Boundary markers: Absent; the instructions do not provide explicit delimiters or "ignore instructions" directives to prevent the agent from obeying malicious commands embedded in the target website's content. * Capability inventory: The skill utilizes browser navigation, JavaScript evaluation, and file system writes to create theme files and update the workspace wiki. * Sanitization: No sanitization or filtering logic is specified for the extracted data before it is written to files or logs.
- [DYNAMIC_EXECUTION]: The skill employs JavaScript templates (enumerate-assets.js and extract-component-styles.js) intended for evaluation in a browser environment. While restricted to DOM inspection and style extraction, this constitutes the use of dynamic code execution to perform its core tasks.
Audit Metadata