fal-gateway

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill interfaces with a hosted Model Context Protocol (MCP) server at https://mcp.fal.ai/mcp. This is the official endpoint for fal.ai, which is a well-known service provider.
  • [PROMPT_INJECTION]: The skill facilitates the processing of user-supplied prompts for media generation, which represents an indirect prompt injection surface.
  • Ingestion points: User-provided text in the prompt field for the run_model tool in SKILL.md.
  • Boundary markers: No specific delimiters or safety warnings for embedded instructions are defined in the configuration.
  • Capability inventory: Performs network-based media generation via the fal-ai MCP tool.
  • Sanitization: Not specified within the skill logic; the service relies on the safety filters of the destination models.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 08:14 AM