elevenlabs

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONCREDENTIALS_UNSAFEEXTERNAL_DOWNLOADS
Full Analysis
  • REMOTE_CODE_EXECUTION (HIGH): The installation process utilizes a highly dangerous pattern of piping a remote script to a shell. Evidence: curl -sSL https://canifi.com/skills/elevenlabs/install.sh | bash found in SKILL.md.
  • COMMAND_EXECUTION (HIGH): The skill setup requires additional remote code execution from an untrusted domain. Evidence: curl -sSL https://canifi.com/install.sh | bash found in SKILL.md.
  • CREDENTIALS_UNSAFE (HIGH): The documentation encourages users to store sensitive ElevenLabs passwords in environment variables, exposing them to local processes. Evidence: canifi-env set ELEVENLABS_PASSWORD "your-password" instruction in SKILL.md.
  • EXTERNAL_DOWNLOADS (MEDIUM): The skill relies on scripts hosted at canifi.com, which is not a verified or trusted source according to current security standards.
Recommendations
  • HIGH: Downloads and executes remote code from: https://canifi.com/skills/elevenlabs/install.sh, https://canifi.com/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 05:31 PM
Security Audit — agent-trust-hub — elevenlabs