paper-to-code — 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

  This skill automates the generation and execution of code derived from ML research papers. It is primarily vulnerable to indirect prompt injection through untrusted paper content and risks arbitrary command execution via an automated debugging loop that runs generated code.

  Risk: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSFeb 22, 2026Full report

• Socket

  pass

  No alerts

  Feb 22, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · No issues

  Risk: MEDIUMFeb 22, 2026Full report

• Runlayer

  warn

  2/2 files flagged

  Risk: MEDIUMFeb 23, 2026Full report