theme-factory
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Trusted Source (SAFE): The skill is authored by Anthropic and hosted within an official repository for agent skills, which is a trusted organization and source.
- No Code (SAFE): The skill package contains no executable scripts (Python, Node.js, or Shell). It operates solely through prompt-based instructions and static markdown files containing theme tokens.
- Data Access (SAFE): The skill only interacts with its internal theme definition files and does not attempt to access sensitive system paths, environment variables, or external network resources.
- Indirect Prompt Injection (SAFE): While the skill allows for custom theme generation based on user descriptions, this is a low-risk data ingestion surface that only influences the generation of visual styling tokens (hex codes and font names) and lacks access to dangerous capabilities or sensitive data for exploitation.
Audit Metadata