fal-ai-media
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill setup involves downloading the
fal-ai-mcp-serverpackage from the npm registry usingnpxfor use as an MCP server. - [COMMAND_EXECUTION]: The skill provides configuration for the agent to initialize the media generation environment by executing the
npxcommand. - [INDIRECT_PROMPT_INJECTION]: The skill functions by interpolating user-provided text prompts and external resource URLs (images/videos) into instructions for remote AI models. While this presents an attack surface where untrusted data could influence model output, it is an inherent part of the skill's media generation purpose and lacks direct access to sensitive system resources.
Audit Metadata