breathing-brand
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill's instructions and reference materials were thoroughly audited for malicious patterns. No evidence of credential theft, unauthorized command execution, or data exfiltration was found. The skill's operations are confined to generating text and design specifications based on internal templates.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied brand names and positioning statements to populate templates for branding specifications and image generation prompts. This represents a typical data ingestion surface for personalizing outputs in this category of skill.
- [EXTERNAL_DOWNLOADS]: The README file provides setup instructions referencing the developer's official GitHub repository and a specific package for installation. These references point to the vendor's own infrastructure and are standard for skill distribution.
Audit Metadata