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 Bash tool to execute belt CLI commands, such as belt login and belt app run elevenlabs/sound-effects, to interface with remote AI models.
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the belt-sh/cli package and references other skills from the inference-sh organization. It also fetches documentation from a public GitHub repository at raw.githubusercontent.com/inference-sh/skills/.
  • [PROMPT_INJECTION]: The skill ingests untrusted user data via the text parameter 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 text and duration_seconds parameters provided in the belt app run command in SKILL.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
Risk Level
SAFE
Analyzed
Aug 6, 2026, 05:03 AM
Security Audit — agent-trust-hub — elevenlabs-sound-effects