elevenlabs-music
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes a
terminaltool to facilitate background job monitoring for music generation tasks. - Evidence: In the 'Deliver' section for chat applications, the instructions specify arming a background command using
terminal(command="sleep <N> && echo elevenlabs music job <job_id>", ...)to notify the agent when a task is ready for status checking. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user data, creating a surface for indirect prompt injection.
- Ingestion points: User-provided song prompts, lyrics, and local file paths for audio/video processing in
SKILL.md. - Boundary markers: Absent; the instructions do not include specific delimiters or warnings to ignore instructions embedded within user lyrics or prompts.
- Capability inventory: The skill possesses the ability to execute shell commands via the
terminaltool and perform network operations through the ElevenLabs API tools. - Sanitization: Absent; user-provided text is passed directly into tool arguments without explicit filtering or sanitization logic mentioned.
Audit Metadata