visual-acceptance-review
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a standard visual regression testing workflow without any detected malicious patterns. It includes clear preflight gates and hard rules that prevent unauthorized code modifications or redesigns.
- [COMMAND_EXECUTION]: The skill instructs the agent to use browser automation tools (such as Playwright) or existing project scripts (e.g.,
pnpm screenshot) to capture screenshots for comparison. These operations are restricted to the intended purpose of visual validation and the acquisition of browser health logs. - [EXTERNAL_DOWNLOADS]: No remote code downloads, external scripts, or unauthorized package installations are requested. References to external reviewers are managed as auxiliary confidence sources and do not involve fetching untrusted content from the internet.
Audit Metadata