mage-outfit-swap

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill operates within the official vendor's infrastructure (mage.space). All tool calls and URLs are vendor-owned, with no unauthorized data exfiltration patterns.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes external image data.
  • Ingestion points: image and additional_images tool parameters.
  • Boundary markers: The skill uses a static prompt template to guide the image generation process.
  • Capability inventory: The skill utilizes image generation, file upload, and request status tools (generate, create_upload, get_request).
  • Sanitization: The skill relies on the Mage platform's internal safety filters, evidenced by explicit handling of content_blocked errors.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 07:16 AM