lavish — 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

  This skill enables the creation and collaborative review of rich HTML artifacts using the lavish-axi CLI tool. It uses npx to execute remote code from the NPM registry and includes a share feature that uploads local content to a third-party hosting service (ht-ml.app). Additionally, it establishes a feedback loop that processes untrusted input from a browser session, which could be used to influence the agent's behavior.

  Risk: MEDIUMREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTIONJul 15, 2026Full report

• Socket

  pass

  No alerts

  Jul 15, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · 1 issue

  Risk: MEDIUMJul 15, 2026Full report