minecraft-modpack-server

Fail

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: HIGHCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires administrative privileges via sudo to install OpenJDK system packages and to open network ports in the firewall using ufw.
  • [REMOTE_CODE_EXECUTION]: The skill downloads a server pack ZIP from a user-supplied URL and executes an unverified bash script (startserver.sh) contained within the archive.
  • [COMMAND_EXECUTION]: The skill establishes persistence by modifying the user's crontab to execute a dynamically generated backup script on an hourly schedule.
  • [COMMAND_EXECUTION]: The skill creates shell scripts (start-minecraft.sh and backup.sh) and modifies their permissions to be executable using chmod +x.
  • [PROMPT_INJECTION]: The skill ingests untrusted user input (Server Name, MOTD, and Download URL) which is then used in shell commands and configuration files without sanitization.
  • Ingestion points: User preference fields and the server pack URL defined in SKILL.md.
  • Boundary markers: No delimiters or ignore instructions are used for the user-provided inputs.
  • Capability inventory: The skill possesses extensive capabilities including sudo execution, crontab modification, and file-writing across SKILL.md.
  • Sanitization: No sanitization or validation steps are performed on the external content before processing.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
May 19, 2026, 07:46 PM
Security Audit — agent-trust-hub — minecraft-modpack-server