elevenlabs-sound-effects
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references installation guidelines and scripts from the inference-sh GitHub repository, which is the official source for the belt CLI tool referenced in the skill's instructions.
- [COMMAND_EXECUTION]: The skill instructs the agent to use the Bash tool to execute belt CLI commands for authentication (belt login) and for running specific sound generation applications (belt app run). These commands are restricted by the allowed-tools configuration to the belt executable.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted user data.
- Ingestion points: User-provided text descriptions are passed to the ElevenLabs sound effect engine through the 'text' parameter in shell commands (SKILL.md).
- Boundary markers: The input is encapsulated within JSON objects passed as arguments to the CLI, providing some structural separation.
- Capability inventory: The skill has access to the Bash tool to execute system commands (SKILL.md).
- Sanitization: There is no explicit evidence of input sanitization or filtering for the user-provided sound descriptions before they are processed by the CLI.
Audit Metadata