webapp-selenium-testing

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates browser automation that ingests untrusted data from web applications into the AI context. Ingestion points include driver.getPageSource(), getText(), and getValue() found in references/page-object-model-base-page.md and references/page-object-model-components.md. The skill lacks strict boundary markers for all ingested data but implements a 50KB truncation limit for page source attachments as a sanitization measure. Capabilities include arbitrary JavaScript execution via JavascriptExecutor and file writing via the project setup script.
  • [DYNAMIC_EXECUTION]: The skill provides examples of using JavascriptExecutor to run scripts within the browser environment (e.g., references/page-object-model-base-page.md, references/wait-strategies-custom-waits.md). This allows for dynamic execution of logic interacting with the target application's DOM, which is controlled by the test script but operates on potentially untrusted page content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 05:39 PM