code-review — 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

  The code review skill is designed to analyze diffs for quality and security, but it contains a high-risk Indirect Prompt Injection vulnerability. The skill instructs the agent to read and follow instructions from external checklist files (like frontend.md or backend.md) that reside within the repository being reviewed. If an attacker includes malicious instructions in these files, they could exploit the agent's powerful toolset—including terminal access (Bash) and file modification capabilities—to compromise the host system.

  Risk: HIGHCOMMAND_EXECUTIONPROMPT_INJECTIONFeb 15, 2026Full report

• Socket

  pass

  No alerts

  Mar 18, 2026Full report

• Snyk

  fail

  Risk: HIGH · No issues

  Risk: HIGHFeb 17, 2026Full report

• Runlayer

  warn

  3/3 files flagged

  Risk: MEDIUMFeb 26, 2026Full report