screenshot-handling
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill follows best practices for file organization and uses standard tools for its intended purpose.
- [COMMAND_EXECUTION]: Includes instructions for using shell utilities such as
mkdir,mv, andfindto manage screenshot files. These operations are limited to the project environment and are essential for the skill's primary functionality. - [PROMPT_INJECTION]: The skill interacts with external web content via
agent-browser, Playwright, and Puppeteer. While this involves processing untrusted data, the activities are restricted to visual state capture and state verification, which does not introduce significant injection risks beyond standard browser automation.
Audit Metadata