gmgn-cooking — security audits

Flagged by auditors

Independent security partners scan this skill's files for malicious content, prompt injection and risky patterns. Verdicts below come from the skills.sh audit program; each partner links to its full report.

• Gen Agent Trust Hub

  pass

  This skill enables the creation and launch of cryptocurrency tokens across multiple blockchains via the gmgn-cli tool. It incorporates financial risk disclosures and requires explicit user confirmation before executing on-chain transactions. While it follows security best practices for local credential management and transaction signing, it presents a surface for indirect prompt injection where user-supplied token metadata is processed and passed to shell commands without explicit sanitization.

  Risk: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSMay 20, 2026Full report

• Socket

  warn

  1 alert: gptSecurity

  May 20, 2026Full report

• Snyk

  fail

  Risk: CRITICAL · 3 issues

  Risk: CRITICALMay 20, 2026Full report

• ZeroLeaks

  pass

  2 findings · Score: 80/100

  Risk: LOWApr 15, 2026Full report