skills/g1joshi/agent-skills/selenium/Gen Agent Trust Hub

selenium

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFE
Full Analysis
  • [Documentation Accuracy] (SAFE): The content consists of legitimate Python code snippets and architectural patterns for web automation.
  • [No Code Execution] (SAFE): No shell commands, installation scripts, or remote code downloads are present in the provided file.
  • [Data Security] (SAFE): No hardcoded credentials or sensitive file path access were identified.
  • [Indirect Prompt Injection Surface] (LOW): As a browser automation tool, any agent using this skill to scrape the web will be exposed to indirect prompt injection from untrusted web content. This is a characteristic of the use-case rather than a flaw in the provided instructions.
  • Ingestion points: Browser get() and find_element() methods interact with external websites.
  • Boundary markers: None present in code snippets.
  • Capability inventory: Subprocess calls and browser automation via selenium.webdriver.
  • Sanitization: None present in code snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 08:48 PM