threejs-audio-generator
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input data which is then transmitted to a remote API, creating a surface for indirect prompt injection.
- Ingestion points: The
--promptand--textarguments inscripts/threejs_audio_asset.pyaccept arbitrary strings, and the--inputflag accepts external audio files. - Boundary markers: The script does not implement delimiters or safety instructions to prevent the remote API from interpreting malicious content within the user-provided strings.
- Capability inventory: The skill possesses network communication capabilities (
urllib.request) and file system access (pathlibfor reading and writing audio files). - Sanitization: Input strings and audio data are passed directly to the ElevenLabs API without internal sanitization or validation of the content.
- [EXTERNAL_DOWNLOADS]: The Python script performs network operations to fetch generated audio content.
- The script connects to
api.elevenlabs.io, which is a well-known service for audio generation. - [COMMAND_EXECUTION]: The skill instructions provide several commands to execute a local Python script for asset generation and processing.
- The commands involve generating sound effects (SFX), text-to-speech (TTS), and audio isolation, which are consistent with the skill's stated purpose.
Audit Metadata