theme-factory
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or behaviors were identified. The skill serves as a static configuration repository for visual styles and design tokens.
- [NO_CODE]: The skill consists entirely of markdown and text documentation; it does not contain or execute any scripts, binaries, or third-party dependencies, which significantly limits the potential for malicious behavior.
- [INDIRECT_PROMPT_INJECTION]: The capability to generate custom themes based on user input in the 'Create your Own Theme' section represents an indirect prompt injection surface area. The risk is minimized by the limited scope of action (generating styling metadata).
- Ingestion points: User-provided descriptions for custom themes in SKILL.md.
- Boundary markers: None present to delimit user input from agent instructions.
- Capability inventory: Tools for modifying or styling artifacts (slides, docs, HTML) as implied by the skill description.
- Sanitization: No input validation or sanitization routines are specified for user-provided theme descriptions.
Audit Metadata