threejs-audio-generator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a Python utility,
scripts/threejs_audio_asset.py, which is intended to be executed by the agent or user. This script uses standard libraries to handle file I/O and network communication with the ElevenLabs API to generate sound files. - [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because it processes external data (prompts, text, and audio files) which could contain instructions intended to influence the agent's behavior if the data source is untrusted.
- Ingestion points: Untrusted data enters the skill via the
--prompt,--text, and--inputcommand-line arguments inscripts/threejs_audio_asset.py. - Boundary markers: The skill does not employ explicit delimiters or instructions to ignore potential commands embedded within the text or audio inputs.
- Capability inventory: The skill possesses the ability to make HTTPS requests to the ElevenLabs API and write generated audio files to paths specified by the user on the local filesystem.
- Sanitization: Input text and metadata are passed to the API using standard JSON encoding, but no specific sanitization, filtering, or validation of the content for malicious instructions is performed.
Audit Metadata