mastra-demo
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill relies on parsing and executing instructions from a user-generated
DEMO_SCRIPT.mdfile across several commands includingaudio.md,record.md, andcompose.md. - Ingestion points: Data is ingested from the
DEMO_SCRIPT.mdfile, specifically thevoiceoverandactionsfields. - Boundary markers: The skill does not define specific boundary markers or "ignore" instructions when processing the script content.
- Capability inventory: The skill possesses significant capabilities, including executing shell commands via the
Bashtool (curl, ffmpeg, ffprobe, npm, npx) and performing browser automation via theclaude-in-chromeMCP server. - Sanitization: No explicit sanitization or escaping mechanisms are described for the text extracted from the script before it is passed to shell commands or browser automation tools.
- [EXTERNAL_DOWNLOADS]: The skill performs downloads from well-known and reputable services necessary for its stated purpose.
- Fetches audio files from the ElevenLabs API (
api.elevenlabs.io). - Installs standard project dependencies from the NPM registry during project initialization (
npm install). - [COMMAND_EXECUTION]: The skill executes several legitimate utility commands to perform video and audio processing.
- Uses
ffprobeto extract duration and metadata from media files. - Uses
ffmpegfor audio concatenation and preview generation. - Uses
npmandnpx remotionfor managing the video project lifecycle and rendering the final output.
Audit Metadata