theme-factory
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill provides curated design themes consisting of color hex codes and font names. It contains no executable code, script files, or system configuration changes.
- [NO_CODE]: No scripts or software packages are included with the skill. All themes are defined in Markdown format, and the logic for applying these themes relies on the agent's core capabilities rather than skill-provided execution.
- [DATA_EXFILTRATION]: There are no network requests, API calls, or remote resource fetches defined in the skill, preventing data exfiltration risks.
- [SAFE]: The skill allows the creation of custom themes based on user-provided descriptions. This represents a data ingestion surface, but the instructions include a mandatory human-in-the-loop review step ('show it for review and verification') before any styling is applied, mitigating risks of unintended behavior. Ingestion points: User-provided descriptions for custom themes in SKILL.md. Boundary markers: No delimiters specified. Capability inventory: None (relies on agent tools). Sanitization: Manual review step required before application.
Audit Metadata