gpt-slide-design
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions guiding an AI to extract design systems from slide images. There are no instructions that attempt to override safety filters or bypass agent constraints.
- [NO_CODE]: The skill does not include any Python or Node.js scripts, executables, or external package dependencies.
- [SAFE]: No network operations, file system access, or credential-related activities were detected.
- [SAFE]: While the skill processes untrusted input in the form of images or PDFs, it lacks any tool access or execution capabilities (capability inventory is empty), neutralizing the risk of indirect prompt injection.
Audit Metadata