skills/lu1sdv/skillsmd/zeroclaw/Gen Agent Trust Hub

zeroclaw

Fail

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill facilitates the execution of a remote bootstrap script via curl -fsSL https://raw.githubusercontent.com/zeroclaw-labs/zeroclaw/main/scripts/bootstrap.sh | bash. This allows unverified remote code to run with the privileges of the local user.\n- [EXTERNAL_DOWNLOADS]: Downloads scripts and refers to binaries from the zeroclaw-labs GitHub organization, which is not a pre-approved trusted source.\n- [COMMAND_EXECUTION]: The skill utilizes powerful CLI commands for service installation, daemon management, and gateway hosting, which perform privileged system operations.\n- [CREDENTIALS_UNSAFE]: References the management of sensitive authentication profiles and secret keys stored in ~/.zeroclaw/auth-profiles.json and ~/.zeroclaw/.secret_key for various AI providers.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/zeroclaw-labs/zeroclaw/main/scripts/bootstrap.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Mar 14, 2026, 04:37 PM