theme-factory

Warn

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: MEDIUMPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (MEDIUM): The 'Create your Own Theme' functionality accepts unvalidated user descriptions to generate styling specifications for artifacts.
  • Ingestion points: User-provided descriptions for custom theme generation in the 'Create your Own Theme' section.
  • Boundary markers: Absent. The instructions do not specify any delimiters or warnings to ignore instructions within the user input.
  • Capability inventory: The skill modifies external artifacts including slides, documents, and HTML landing pages (write capability).
  • Sanitization: Absent. There is no mention of filtering or escaping user-provided text. A malicious user could provide a theme description containing instructions that the agent might obey while generating or applying the theme to artifacts.
  • Data Exposure (LOW): The skill references reading files from a themes/ directory based on selection. While no explicit code is provided, there is a potential for path traversal if the agent does not strictly validate the theme name before file access.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:01 PM