parallel-deep-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 skill is functional for performing deep research but contains a security risk where user-provided text is directly inserted into shell commands, potentially allowing for command or argument injection. It also processes external web content which presents a minor surface for indirect prompt injection.

  Risk: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTIONSAFEMay 24, 2026Full report

• Socket

  pass

  No alerts

  May 24, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · 1 issue

  Risk: MEDIUMMay 24, 2026Full report

• Runlayer

  pass

  1/1 file flagged

  Risk: LOWMar 3, 2026Full report

• ZeroLeaks

  pass

  1 finding · Score: 82/100

  Risk: LOWApr 16, 2026Full report