krea-archviz
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill provides detailed instructions for architectural visualization workflows, material descriptions, and lighting recipes.
- [DATA_EXFILTRATION]: No sensitive data access or exfiltration patterns were found. The skill uses standard MCP tools to interact with the Krea AI service, which is consistent with its stated purpose as a vendor-provided tool.
- [REMOTE_CODE_EXECUTION]: No remote code execution, dynamic code generation, or unauthorized package installation patterns were identified.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided images and text prompts to generate renders. While this represents a standard attack surface for indirect prompt injection, it is the primary function of the skill and no specific vulnerabilities or instructions to bypass safety filters were found.
Audit Metadata