heuristic
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is strictly instructional and focuses on generating a UI audit report. It does not request or utilize any sensitive permissions, perform network requests, or execute shell commands.
- [SAFE]: References to external files such as
references/heuristics.mdandreferences/personas.mdare local to the skill's context for methodology loading. - [SAFE]: The comment regarding
node scripts/sync-harnesses.mjsis standard developer metadata for an auto-generated file and is not presented as an instruction for the AI agent to execute at runtime.
Audit Metadata