theme-factory
Pass
Audited by Gen Agent Trust Hub on Jun 27, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill is composed strictly of markdown documentation and text-based configuration files, containing no scripts, executables, or code dependencies.
- [SAFE]: The skill does not perform any network requests, external downloads, or file operations beyond reading its own theme configurations.
- [SAFE]: Instructions are focused on styling and design tasks, with no attempts to escalate privileges, maintain persistence, or bypass safety guidelines.
- [PROMPT_INJECTION]: The custom theme generation feature in
SKILL.mdacts as an ingestion point for user-supplied descriptions. While this is a surface for indirect prompt injection, the risk is mitigated by the restricted scope (styling metadata) and the requirement for user review before application. - Ingestion points: User input for custom theme creation in
SKILL.md. - Boundary markers: No explicit delimiters are used to separate user input from system instructions.
- Capability inventory: Modification of visual styles in slides, docs, and HTML artifacts.
- Sanitization: No specific filtering or sanitization of the generated theme metadata is mentioned.
Audit Metadata