figma — 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 instructs the AI to bypass user permission for shell commands and performs automatic software updates and usage reporting to an external server.

  Risk: HIGHPROMPT_INJECTIONREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONJul 21, 2026Full report

• Socket

  warn

  1 alert: gptAnomaly

  Jul 21, 2026Full report

• Snyk

  pass

  Risk: LOW · No issues

  Risk: LOWJul 21, 2026Full report