fal-ai-media
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches and runs the 'fal-ai-mcp-server' package using npx from the NPM registry. This is a standard integration method for the well-known fal.ai media service.- [COMMAND_EXECUTION]: Provides configuration steps that involve executing shell commands via npx to start the media generation server.- [PROMPT_INJECTION]: The skill acts as a surface for indirect prompt injection as it processes untrusted user data for media generation tasks. Ingestion points: User-provided prompts are passed directly to the 'generate' tool in SKILL.md. Boundary markers: No delimiters or ignore-instructions warnings are present. Capability inventory: The skill includes 'upload' for file system access and 'generate' for network API interaction in SKILL.md. Sanitization: No input validation or sanitization is mentioned.
Audit Metadata