rtk-setup
Fail
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The workflow in SKILL.md includes the command
curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | sh. This technique executes a remote script without any integrity checks or human review, allowing for potential system compromise if the remote source is malicious or hijacked. - [EXTERNAL_DOWNLOADS]: The skill relies on external resources from a third-party GitHub organization (rtk-ai). These resources are fetched at runtime without version pinning or hash verification.
- [COMMAND_EXECUTION]: The skill uses several shell commands including
brew install,rtk --version,which, andgrepto install software and verify environment state. It systematically modifies workspace files (RTK.md and AGENTS.md) to force subsequent agent actions through the installed binary.
Recommendations
- HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata