theme-factory

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFE
Full Analysis
  • SAFE (SAFE): No security issues detected in the analysis of the skill. The skill's functionality is limited to reading local configuration files and providing design suggestions based on those files or user input.
  • Indirect Prompt Injection (LOW): While the skill ingests data from local theme files and user-provided descriptions for custom themes, these are processed as styling data rather than executable instructions. The capability surface is restricted to styling artifacts.
  • Ingestion points: themes/*.md files and user input for custom themes.
  • Boundary markers: None explicitly defined in the prompt instructions, but the data source is internal to the skill.
  • Capability inventory: Modifying styling (colors/fonts) of artifacts (slides, HTML, docs).
  • Sanitization: Standard LLM processing of user input for custom theme generation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 02:07 PM