pixellab
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a standard documentation and integration guide for the PixelLab MCP server. It does not contain any obfuscated code, unauthorized network requests, or attempts to access sensitive system data.
- [INDIRECT_PROMPT_INJECTION]: While the skill accepts user-provided text descriptions to guide the AI generation process, the risk is minimal as the output is restricted to pixel art assets rather than executable instructions or text. 1. Ingestion points: 'description' and 'action_description' parameters in asset creation tools defined in SKILL.md. 2. Boundary markers: Not explicitly defined in the prompts. 3. Capability inventory: Tool capabilities are strictly limited to pixel art asset management (create, get, list, delete) via the mcpc CLI; no shell access or general file system manipulation is provided. 4. Sanitization: Input validation is handled by the underlying PixelLab service.
Audit Metadata