ux-heuristic-review
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and provides a framework for manual UX reviews. It does not contain any executable scripts, shell commands, or network-enabled tools.
- [SAFE]: No hardcoded credentials, sensitive path access, or exfiltration patterns were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process untrusted external data such as UI prototypes and source code (ingestion points in SKILL.md). While no explicit boundary markers or sanitization methods are defined, the skill lacks any capabilities for subprocess calls, network access, or file modification (capability inventory), rendering the surface non-exploitable.
Audit Metadata