brand-guidelines
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided artifacts and text for branding purposes, which represents an indirect prompt injection surface.\n
- Ingestion points:
SKILL.mdspecifies applying styling to any artifact, including headings and body text provided by the user.\n - Boundary markers: There are no instructions providing delimiters or directing the agent to ignore instructions embedded within the processed content.\n
- Capability inventory: The skill directs the agent to utilize the
python-pptxlibrary to apply RGB colors and font styles.\n - Sanitization: The instructions do not include any steps for sanitizing or validating user-provided input before processing.\n- [SAFE]: The skill references legitimate and well-known accessibility auditing services, including WebAIM and Adobe Color, to ensure brand compliance with accessibility standards.
Audit Metadata