elevenlabs-voice-isolator

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references installation instructions from a remote Markdown file on GitHub and suggests using npx skills add to fetch additional components from the inference-sh/skills repository.
  • [COMMAND_EXECUTION]: The skill uses the infsh CLI tool to execute audio processing tasks. This involves running shell commands that incorporate user-provided parameters, such as audio source URLs.
  • [PROMPT_INJECTION]: The skill ingest untrusted data in the form of audio files from external URLs. This creates an indirect prompt injection surface where instructions could be embedded in the data or metadata of the audio, though the risk is mitigated by the use of structured JSON inputs and the specific nature of the isolation tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 09:05 PM