selenium
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of technical documentation and code examples for web browser automation using Selenium. The content is educational and follows established software testing patterns such as the Page Object Model (POM).
- [EXTERNAL_DOWNLOADS]: The skill mentions 'Selenium Manager' and 'webdriver-manager'. These are legitimate tools used in the Selenium ecosystem to automatically manage browser driver binaries (e.g., ChromeDriver, GeckoDriver) by downloading them from official browser vendor repositories.
- [INDIRECT_PROMPT_INJECTION]: The skill enables an agent to automate web browsers, which involves ingesting data from external, untrusted websites. This constitutes a potential attack surface where the agent could encounter and process malicious instructions embedded in web pages.
- Ingestion points: External web content is retrieved via the
driver.get()method as shown inSKILL.md. - Boundary markers: There are no specific delimiters or instructions provided to the agent to treat page content as data only or to ignore embedded instructions.
- Capability inventory: The skill enables full browser automation, including site navigation, element interaction, and form submission.
- Sanitization: No sanitization or filtering of web content is demonstrated in the provided code snippets.
Audit Metadata