brand-guidelines
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists of informational markdown files and style definitions. No malicious patterns, obfuscation, or unauthorized data access attempts were detected.\n- [NO_CODE]: The package does not include any scripts, binaries, or automated installation processes. It relies on documentation to guide the agent's behavior.\n- [EXTERNAL_DOWNLOADS]: References official and well-known documentation and testing tools from established organizations such as WebAIM, Adobe, and Coolors. These links are provided for reference and do not involve the execution of remote code.\n- [PROMPT_INJECTION]: The skill is intended to process external artifacts to apply styling, which presents an indirect surface for processing untrusted data. This is assessed as safe as the skill provides only formatting instructions.\n
- Ingestion points: User-supplied documents and artifacts.\n
- Boundary markers: Not specified in instructions.\n
- Capability inventory: Visual styling via agent tools such as python-pptx.\n
- Sanitization: No content validation or escaping of input artifact data is defined.
Audit Metadata