brand-guidelines
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied artifacts to apply brand styling, creating an ingestion surface for external data.
- Ingestion points: The skill applies formatting to any artifact provided to the agent as described in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters for separating user content from system instructions.
- Capability inventory: The skill uses the python-pptx library to modify presentation files.
- Sanitization: No explicit validation or filtering of input content is specified.
- [DYNAMIC_EXECUTION]: Technical details in SKILL.md mention the use of the python-pptx RGBColor class, indicating the agent will generate and execute Python code to manipulate document properties. This is standard functionality for document styling tasks.
Audit Metadata