Skills
Navigate
skills/nagi-inaba/claude-code-setup/fal-ai-media/Gen Agent Trust Hub

fal-ai-media

Pass

Audited by Gen Agent Trust Hub on Mar 30, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download of the fal-ai-mcp-server package from the npm registry using npx during the setup process.
  • [COMMAND_EXECUTION]: Provides instructions to configure and execute the fal-ai MCP server within the ~/.claude.json file.
  • [DATA_EXFILTRATION]: Includes a Python code example that sends text data to ElevenLabs' official API and an upload tool that transmits user-specified local files to fal.ai's cloud infrastructure for processing.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by processing natural language prompts to drive AI model generations.
  • Ingestion points: User-provided prompt strings and text inputs for image, video, and audio generation.
  • Boundary markers: Absent in the provided code examples.
  • Capability inventory: Remote API generation calls via the generate tool, file uploads via the upload tool, and local file writing in the ElevenLabs Python snippet.
  • Sanitization: Absent; the skill relies on service-side safety protocols.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 30, 2026, 08:58 AM