creative-moodboard
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and workflow were evaluated for malicious patterns, including prompt injection, obfuscation, and data exfiltration. No security threats were identified.
- [COMMAND_EXECUTION]: The skill utilizes the local file system to store and organize generated image tiles within project subdirectories (./creative/moodboard/). This is a documented and expected behavior for managing creative assets.
- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes untrusted user input to define territories and generate image prompts. Ingestion points: User-provided brand, audience, and asset data in SKILL.md. Boundary markers: Absent. Capability inventory: Local file system writes and image generation tool usage in SKILL.md. Sanitization: Absent.
Audit Metadata