fal-ai-media

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install the fal-ai-mcp-server via npx. This package is the official tool for interacting with the fal.ai media generation service.
  • [COMMAND_EXECUTION]: Recommended configuration involves executing the MCP server using npx, which is a common practice for running Node.js-based tools.
  • [DATA_EXFILTRATION]: Provides a Python template that utilizes the requests library to communicate with the ElevenLabs API (api.elevenlabs.io). This network activity is used to facilitate legitimate text-to-speech generation.
  • [PROMPT_INJECTION]: The skill processes untrusted user input as prompts for media generation models, creating a surface for indirect prompt injection.
  • Ingestion points: User-defined strings in the prompt and text parameters across various tools and code snippets.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt templates.
  • Capability inventory: The skill uses tools for file uploading (upload), network-based generation (generate), and external API calls via Python (requests).
  • Sanitization: There is no evidence of input sanitization or validation before the prompts are sent to the AI models.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 02:28 AM