elevenlabs-voice-isolator

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of the belt-sh/cli tool and other related skills from the inference-sh organization. These are well-known resources associated with the inference.sh platform for which this skill is designed.
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with external audio data by passing URLs to the belt CLI tool.
  • Ingestion points: Audio URLs are passed as arguments to the belt app run command in SKILL.md examples.
  • Boundary markers: The skill uses JSON objects to structure the input arguments, reducing the risk of argument injection.
  • Capability inventory: The skill is restricted to running the belt command via Bash(belt *) in the allowed-tools configuration.
  • Sanitization: Not applicable as the skill primarily provides documentation for CLI usage rather than complex script logic.
  • [SAFE]: No malicious patterns such as obfuscation, credential exfiltration, or unauthorized command execution were detected. The skill's configuration limits the agent's actions to a specific, legitimate tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 10:59 PM
Security Audit — agent-trust-hub — elevenlabs-voice-isolator