swarm — 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

  pass

  The skill is a comprehensive orchestration layer designed for parallel agent execution. It integrates with multiple backends (Claude Native Teams, Codex, and gc) and manages task lifecycles using a shared filesystem and the TaskList API. No malicious patterns or security risks were identified beyond the inherent risks of managing sub-agents.

  Risk: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONMay 23, 2026Full report

• Socket

  pass

  No alerts

  May 23, 2026Full report

• Snyk

  pass

  Risk: LOW · No issues

  Risk: LOWMay 23, 2026Full report

• Runlayer

  fail

  8/13 files flagged

  Risk: HIGHMar 15, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report