babylon-audio-generator
Pass
Audited by Gen Agent Trust Hub on Aug 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The wrapper script
scripts/babylon_audio_asset.pydynamically calculates and adds a relative path (../../threejs-audio-generator/scripts) to the Python search path to import its main logic. This is an intended mechanism for its role as a mirror skill.\n- [PROMPT_INJECTION]: The skill accepts external text input via the--textargument without explicit validation or boundary markers, presenting a vulnerability surface where malicious instructions in processed data could potentially influence agent behavior.\n - Ingestion points: Input provided to the
--textargument inscripts/babylon_audio_asset.py.\n - Boundary markers: None identified in the provided skill instructions or scripts.\n
- Capability inventory: Audio file generation and asset preparation via ElevenLabs (delegated).\n
- Sanitization: No sanitization or filtering logic is implemented in the wrapper script.
Audit Metadata