changelog-generator — 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

  This markdown-based skill is highly vulnerable to indirect prompt injection. It directs an agent to analyze untrusted git commit history and perform file system writes without providing security boundaries or sanitization instructions, which could allow malicious commit messages to hijack the agent's behavior.

  Risk: HIGHPROMPT_INJECTIONCOMMAND_EXECUTIONNO_CODEFeb 15, 2026Full report

• Socket

  pass

  No alerts

  Mar 18, 2026Full report

• Snyk

  pass

  Risk: LOW · No issues

  Risk: LOWFeb 17, 2026Full report

• Runlayer

  pass

  1 file scanned · No issues

  Risk: NONEFeb 26, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report