moodboard-builder
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a structured workflow for creative tasks and contains no executable scripts, commands, or remote dependencies. All content consists of plain-text instructions and templates for the AI agent to follow.
- [PROMPT_INJECTION]: No evidence of prompt injection or instruction override patterns was found. The instructions are focused on guiding the creative process without attempting to bypass safety filters or ignore system rules.
- [DATA_EXFILTRATION]: There are no commands or instructions that access sensitive local files or perform network operations. The skill relies entirely on user-provided inputs within the chat session.
- [OBFUSCATION]: No obfuscated strings, hidden characters, or encoding techniques were detected in the skill's content.
- [INDIRECT_PROMPT_INJECTION]: While the skill ingests user input regarding brand details, it does not process untrusted external data sources (like URLs or third-party APIs) that could lead to indirect prompt injection. The risk is negligible as it follows a rigid internal template.
Audit Metadata