taste-brandkit
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for image generation art direction. No malicious patterns, executable code, or scripts were detected in the provided files.
- [PROMPT_INJECTION]: The instructions do not contain any bypass markers, role-play injections (DAN), or directives to ignore safety guidelines. The use of instructional headers like 'CORE PRINCIPLE' and 'TEXT RULES' is benign and consistent with the skill's purpose.
- [DATA_EXFILTRATION]: No network operations (such as curl, wget, or fetch) or access to sensitive file paths (e.g., ~/.ssh, .env) were found. The skill does not attempt to exfiltrate data.
- [REMOTE_CODE_EXECUTION]: The skill does not include any package installation commands (npm, pip) or remote script execution patterns. It relies purely on the agent's internal reasoning and image generation capabilities.
Audit Metadata