add-expert — 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

  fail

  The skill enables an agent to modify source code (.tsx) and execute local build commands using unvalidated external input. This creates a high risk of code injection and execution of malicious payloads if the input data is compromised.

  Risk: HIGHCOMMAND_EXECUTIONPROMPT_INJECTIONFeb 16, 2026Full report

• Socket

  pass

  No alerts

  Mar 18, 2026Full report

• Snyk

  pass

  Risk: LOW · No issues

  Risk: LOWFeb 16, 2026Full report

• Runlayer

  pass

  1 file scanned · No issues

  Risk: NONEFeb 21, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 15, 2026Full report