opencli-autofix — security audits

Review recommended

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

  warn

  The skill implements an autonomous code-repair loop that modifies and executes local script files (adapters) based on diagnostic output. While intended for fixing broken site connectors, this self-modifying behavior carries risks of executing unintended code changes, especially as the diagnostics include data from external websites.

  Risk: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONMay 3, 2026Full report

• Socket

  pass

  No alerts

  May 3, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · 1 issue

  Risk: MEDIUMMay 3, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report