ui-visual-validator
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and guidelines for a UI validation persona. It does not include any scripts, executables, or automated tools.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for analyzing external visual data (screenshots). While this data represents an untrusted ingestion point, the skill lacks any command execution or data exfiltration capabilities that could be exploited via indirect injection.
- [REMOTE_CODE_EXECUTION]: While the skill mentions various visual testing tools (e.g., Chromatic, Percy, Applitools), these are listed as domain knowledge areas for the AI persona to reference, not as commands to be executed or packages to be installed.
Audit Metadata