brand-guidelines
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a style guide for applying brand identity (colors and fonts) to content. It does not include executable scripts, network operations, or access to sensitive data.
- [INDIRECT_PROMPT_INJECTION]: The skill acts on external artifacts to apply formatting. While this constitutes a data ingestion surface, the risk is negligible as the instructions are confined to visual design and do not involve complex logic or high-privilege tool execution.
- Ingestion points: Processes user-provided artifacts or content intended for styling (SKILL.md).
- Boundary markers: None provided in the instructions.
- Capability inventory: Mentions the use of the
python-pptxlibrary for applying colors and fonts to presentations. - Sanitization: No specific sanitization or validation of the input content is described.
Audit Metadata