agent-coder — 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 provides a coding agent persona with hooks for task logging and project linting. It contains a shell command injection vulnerability in the pre-hook where the task description is echoed without sanitization, and it runs potentially untrusted scripts via npm in the post-hook.

  Risk: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTIONMar 1, 2026Full report

• Socket

  pass

  No alerts

  Mar 18, 2026Full report

• Snyk

  pass

  Risk: LOW · No issues

  Risk: LOWMar 1, 2026Full report

• Runlayer

  pass

  1 file scanned · No issues

  Risk: NONEMar 2, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report