agentskill.sh
secured
fal-ai-media
Unified media generation via fal.ai MCP — image, video, and audio. Covers text-to-image (Nano Banana), text/image-to-video (Seedance, Kling, Veo 3), text-to-speech (CSM-1B), and video-to-audio (ThinkSound). Use when the user wants to generate images, videos, or audio with AI.
Security score
This tab presents tested categories, issue summaries, and source snippets in an audit-style report.
High / Medium / Low
Categories Tested
Instruction boundariesFilesystem writesNetwork referencesPlatform-specific install flow
Security Issues
Medium
File Access
Line 21
Access to hidden dotfiles in home directory
fal.ai MCP server must be configured. Add to `~/.claude.json`:
Low
External Calls
Line 31
External URL reference
Get an API key at [fal.ai](https://fal.ai).
Low
External Calls
Line 216
External URL reference
"https://api.elevenlabs.io/v1/text-to-speech/<voice_id>",
Mitigations
Review the upstream repository before copying files into a local skills directory.
Confirm install instructions and supported runtimes against SKILL.md instead of a generic readme.