citation-management — 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 skill attempts to access sensitive credentials by reading from a hardcoded file path on the host system and utilizes shell command substitution to execute logic on the machine.

  Risk: HIGHCREDENTIALS_UNSAFECOMMAND_EXECUTIONDATA_EXFILTRATIONFeb 22, 2026Full report

• Socket

  warn

  1 alert: gptSecurity

  Feb 22, 2026Full report

• Snyk

  fail

  Risk: HIGH · No issues

  Risk: HIGHFeb 22, 2026Full report

• Runlayer

  warn

  3/3 files flagged

  Risk: MEDIUMFeb 23, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report