research — security audits

Review recommended

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

  warn

  The research skill automates deep codebase exploration and knowledge synthesis. While highly functional, it contains shell command templates that directly interpolate user-provided topics, which could lead to command injection if malicious topics are provided. It also accesses files in the global ~/.claude directory and manages multiple sub-agents, creating a significant security surface that requires careful oversight.

  Risk: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTIONREMOTE_CODE_EXECUTIONMay 24, 2026Full report

• Socket

  warn

  1 alert: gptAnomaly

  May 24, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · 1 issue

  Risk: MEDIUMMay 24, 2026Full report

• Runlayer

  warn

  5/13 files flagged

  Risk: MEDIUMMar 10, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report