skills/xixu-me/xget/xget/Gen Agent Trust Hub

xget

Warn

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions prioritize direct action over instruction, directing the agent to "run the needed shell commands" and "edit the real files" directly for tasks like migration or deployment.\n- [REMOTE_CODE_EXECUTION]: The workflow involves fetching "live README guidance" from a remote repository using scripts/xget.mjs and subsequently executing shell commands extracted from that content. This creates a bridge where remote content can influence local system execution.\n- [EXTERNAL_DOWNLOADS]: The helper script scripts/xget.mjs is configured to download a platform catalog from raw.gitcode.com and a README file from raw.githubusercontent.com.\n- [COMMAND_EXECUTION]: The skill instructions include patterns for modifying shell profile files such as ~/.bashrc, ~/.zshrc, and PowerShell profiles to persist environment variables.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes remote markdown content (from the README) and is instructed to execute commands derived from it.\n
  • Ingestion points: scripts/xget.mjs fetches README.md from GitHub.\n
  • Boundary markers: None identified for the fetched content.\n
  • Capability inventory: Shell command execution and file-write capabilities are explicitly granted in SKILL.md.\n
  • Sanitization: None; the script only performs string replacement for URLs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 28, 2026, 09:07 AM