theme-factory
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided descriptions to generate custom font and color themes, creating a surface for indirect prompt injection where malicious instructions could be embedded in the design requests.
- Ingestion points: User input for creating custom themes as described in SKILL.md.
- Boundary markers: None; the instructions do not specify the use of delimiters or boundary markers for user-supplied input.
- Capability inventory: The skill applies visual styles (colors and fonts) to various artifacts like slides, reports, and HTML pages.
- Sanitization: The skill includes a mitigation step requiring the agent to display the generated theme for user review and verification before applying it to any artifact.
- [SAFE]: The skill references font resources from Google Fonts in the font-pairing-guide.md file, which is a recognized and trusted service.
Audit Metadata