playground — 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

  This skill generates interactive HTML files from external data and then instructs the agent to execute them locally using the 'open' command. It lacks any security measures to sanitize the input data, creating a significant risk where malicious code or documents could inject harmful scripts into the generated file that then execute in your browser.

  Risk: HIGHCOMMAND_EXECUTIONPROMPT_INJECTIONFeb 15, 2026Full report

• Socket

  pass

  No alerts

  Mar 18, 2026Full report

• Snyk

  pass

  Risk: LOW · No issues

  Risk: LOWFeb 17, 2026Full report

• Runlayer

  pass

  7 files scanned · No issues

  Risk: NONEFeb 26, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report