agent-release-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

  This skill automates software release workflows by integrating GitHub CLI with a vendor-specific orchestration tool. It is susceptible to indirect prompt injection because it ingests untrusted data from commit messages and pull request descriptions without sanitization, which could allow an attacker with repository access to influence the release process or generated changelogs.

  Risk: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONMar 1, 2026Full report

• Socket

  warn

  1 alert: gptSecurity

  Mar 18, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · No issues

  Risk: MEDIUMMar 1, 2026Full report

• Runlayer

  fail

  1/1 file flagged

  Risk: HIGHMar 2, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report