elevenlabs-sound-effects
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to executebeltCLI commands, such asbelt loginandbelt app run elevenlabs/sound-effects, to interface with remote AI models. - [EXTERNAL_DOWNLOADS]: The skill recommends installing the
belt-sh/clipackage and references other skills from theinference-shorganization. It also fetches documentation from a public GitHub repository atraw.githubusercontent.com/inference-sh/skills/. - [PROMPT_INJECTION]: The skill ingests untrusted user data via the
textparameter for sound generation, which is interpolated into a shell command for the CLI tool. This creates a surface for indirect prompt injection. - Ingestion points: The
textandduration_secondsparameters provided in thebelt app runcommand inSKILL.md. - Boundary markers: The inputs are wrapped in a JSON string within single quotes (
--input '{"text": "..."}'), but there are no instructions for escaping internal quotes or special characters. - Capability inventory: The skill has command execution capabilities via the
Bash(belt *)tool. - Sanitization: No sanitization or input validation logic is present in the skill instructions to prevent command injection or model manipulation through the input text.
Audit Metadata