theme-factory
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists exclusively of instructional markdown and configuration files for styling. It does not include executable code, external dependencies, or commands that access sensitive files or perform network requests.
- [INDIRECT_PROMPT_INJECTION]: The skill allows the agent to generate custom themes based on user-provided descriptions. This represents an attack surface where untrusted data (user descriptions) is processed into instructions for styling. However, the scope is limited to visual design parameters, presenting no significant security risk.
- Ingestion points: User-provided descriptions for custom themes as specified in SKILL.md.
- Boundary markers: Absent; there are no specific instructions to ignore embedded commands within user descriptions.
- Capability inventory: Reading local theme markdown files and applying color/font styles to user-facing artifacts.
- Sanitization: Absent; the skill does not explicitly validate or filter the user-provided theme descriptions.
Audit Metadata