elevenlabs-sound-effects

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and installs external components from a well-known service provider.
  • Fetches installation instructions from a public repository at https://raw.githubusercontent.com/inference-sh/skills/refs/heads/main/cli-install.md.
  • Instructs the user to install the belt-sh/cli package via npx.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted user data within its primary workflow.
  • Ingestion points: The text parameter in SKILL.md, which contains the sound effect description, is provided by the user.
  • Boundary markers: There are no explicit delimiters or instructions to the model to ignore embedded commands within the text input.
  • Capability inventory: The skill uses the Bash tool to execute belt app run commands, which involves network communication with the ElevenLabs API.
  • Sanitization: User input is interpolated directly into a JSON payload for the CLI tool without escaping or validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 06:32 PM
Security Audit — agent-trust-hub — elevenlabs-sound-effects