Skills
skills/owenleezy/agent-browser-skill/agent-browser-scrape/Gen Agent Trust Hub

agent-browser-scrape

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the agent-browser CLI to perform actions such as opening URLs, waiting for network idle, and getting element counts. These are standard operations for web automation.
  • [REMOTE_CODE_EXECUTION]: The skill uses eval commands to execute JavaScript within the browser context for the purpose of selecting and mapping web data. This is a standard and expected functionality for a scraping utility.
  • [DATA_EXFILTRATION]: While the skill extracts data from websites, it does not demonstrate patterns of unauthorized access to local sensitive files or exfiltration of credentials to external servers.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 07:48 AM
Security Audit — agent-trust-hub — agent-browser-scrape