pixellab-mcp

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill interacts with the external API https://api.pixellab.ai/mcp and generates direct download links for assets. The documentation notes that these downloads are unauthenticated and rely on UUIDs as access keys.
  • [DATA_EXFILTRATION]: User-provided descriptions and game asset metadata are transmitted to the PixelLab infrastructure. This is the intended purpose of the skill but constitutes external data transmission.
  • [PROMPT_INJECTION]: The skill acts as an ingestion surface for indirect prompt injection via the description parameters in character and tileset creation tools.
  • Ingestion points: description, lower_description, upper_description, and transition_description fields in SKILL.md.
  • Boundary markers: None present in the tool call examples; instructions are interpolated directly into service calls.
  • Capability inventory: Network requests to the PixelLab API for asset generation.
  • Sanitization: No sanitization or validation of input descriptions is specified in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 02:41 AM
Security Audit — agent-trust-hub — pixellab-mcp