custom-metrics — 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

  warn

  The skill accesses the Claude configuration file (~/.claude/config.json) and environment variables to automatically detect API keys. While this is intended for user convenience within the LaunchDarkly ecosystem, it involves reading sensitive configuration data from the local file system.

  Risk: MEDIUMDATA_EXFILTRATIONJun 12, 2026Full report

• Socket

  pass

  No alerts

  Jun 12, 2026Full report

• Snyk

  fail

  Risk: HIGH · 1 issue

  Risk: HIGHJun 12, 2026Full report