fabro-workflow-factory

Fail

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides installation commands that pipe a remote script directly to the bash shell (curl -fsSL https://fabro.sh/install.sh | bash). This practice allows for arbitrary code execution from a domain that is not recognized as a trusted source.
  • [EXTERNAL_DOWNLOADS]: Remote content from https://fabro.sh/install.md is piped directly into the AI agent (| claude) or dynamic execution tools (codex). This method can be used to inject malicious instructions or commands into the agent's workflow.
  • [COMMAND_EXECUTION]: The troubleshooting section instructs users to modify shell configuration files (~/.bashrc, ~/.zshrc) to add the tool to the system path. In combination with unverified installation scripts, this can be leveraged as a persistence mechanism for malicious payloads.
Recommendations
  • HIGH: Downloads and executes remote code from: https://fabro.sh/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 19, 2026, 07:51 AM