theme-factory
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill performs benign styling tasks by reading local configuration files and applying visual attributes to artifacts.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user input for theme selection and generation, representing a standard input surface. However, the risk is minimal as the agent's actions are restricted to applying visual styling parameters (hex codes and font names) to artifacts.
- Ingestion points: User selection of themes and custom theme descriptions are ingested in
SKILL.md. - Boundary markers: None explicitly defined in the instructions.
- Capability inventory: The skill reads local Markdown files in the
themes/directory and is instructed to modify the styling of an artifact. - Sanitization: No specific sanitization logic for user-provided theme descriptions is mentioned, but the output domain is limited to aesthetic properties.
Audit Metadata