elevenlabs-music
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references external installation instructions and related skills from the inference-sh GitHub repository. These are legitimate resources for the tool's intended use and do not involve unauthorized code execution.
- [COMMAND_EXECUTION]: The skill utilizes the belt CLI to execute music generation tasks. The commands correctly pass user parameters to the elevenlabs/music app. All command usage is consistent with the primary purpose of the skill.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text for music prompts and duration settings (Ingestion points: SKILL.md examples). There are no boundary markers or explicit sanitization present for these inputs. The skill's capability inventory includes the Bash tool via the belt CLI to interact with the inference.sh API. This constitutes a standard vulnerability surface for generative AI skills but presents a low risk as the input is consumed by an audio generation model.
Audit Metadata