theme-factory
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided descriptions to generate custom styling themes (colors and fonts). This ingestion of untrusted data creates a potential surface for indirect prompt injection if the generated output is interpreted as instructions by the agent. However, the risk is minimal and mitigated by explicit instructions for user verification.
- Ingestion points: User-provided descriptions for custom theme generation in
SKILL.md. - Boundary markers: The skill does not define specific boundary markers for user input, relying on natural language instructions.
- Capability inventory: The skill's primary capability is reading theme specifications and applying styling (hex codes and font names) to artifacts.
- Sanitization: No specific sanitization or filtering of user input is defined, but the skill includes a mandatory human-in-the-loop review step ('show it for review and verification') before applying custom themes.
- [NO_CODE]: The skill consists entirely of markdown configuration and documentation files. It does not include any scripts (Python, JavaScript, Shell) or binaries, significantly reducing the attack surface for traditional malware or remote code execution.
Audit Metadata