elevenlabs-stt

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the infsh command-line tool to interact with transcription services. The allowed-tools frontmatter configuration (Bash(infsh *)) effectively restricts the agent's shell access to only this specific utility, preventing arbitrary system command execution.
  • [EXTERNAL_DOWNLOADS]: The skill includes links to official installation guides and supplementary skill modules hosted on the author's GitHub repository (github.com/inference-sh). These are recognized vendor resources used for environment setup and tool integration.
  • [SAFE]: No malicious patterns such as prompt injection, obfuscated commands, or persistence mechanisms were detected. The skill's behavior is consistent with its stated purpose of providing transcription and forced alignment capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 09:11 AM