esm — 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 ESM skill provides a comprehensive toolkit for protein language modeling using the ESM3 and ESM C models. While the skill primarily facilitates scientific research and protein engineering, the provided documentation and code snippets include a security anti-pattern using the 'pickle' module for caching and checkpointing. This introduces a risk of arbitrary code execution if used with untrusted local files. Additionally, the skill's ability to process external protein structure files creates a surface for indirect prompt injection.

  Risk: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTIONApr 9, 2026Full report

• Socket

  pass

  No alerts

  Apr 9, 2026Full report

• Snyk

  pass

  Risk: LOW · No issues

  Risk: LOWApr 9, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 15, 2026Full report