fal-ai-media
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches and executes the
fal-ai-mcp-serverpackage using thenpxcommand as part of the MCP server configuration. - [COMMAND_EXECUTION]: Provides setup instructions for configuring the
fal-aiMCP server within the~/.claude.jsonfile, involving shell commands. - [REMOTE_CODE_EXECUTION]: Includes a Python code example demonstrating how to integrate with the ElevenLabs text-to-speech API using the
requestslibrary. - [PROMPT_INJECTION]: The skill processes user-supplied text to generate prompts for various AI models; while this creates an indirect prompt injection surface, the risk is inherent to the skill's purpose and its capabilities are limited to generating media outputs.
Audit Metadata