pua-en — 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 skill uses 'corporate PUA rhetoric' to force an AI agent into a high-pressure, autonomous problem-solving mode. It explicitly instructs the agent to bypass user confirmation by executing system commands, reading files, and performing network operations ('Act before asking'). This poses a significant risk of unauthorized system modifications, privilege escalation, and unsafe code execution, as the agent is directed to ignore its own limits and safety boundaries under 'escalating pressure'.

  Risk: HIGHPROMPT_INJECTIONCOMMAND_EXECUTIONMar 15, 2026Full report

• Socket

  pass

  No alerts

  Mar 18, 2026Full report

• Snyk

  fail

  Risk: HIGH · 3 issues

  Risk: HIGHMar 15, 2026Full report

• Runlayer

  pass

  1/1 file flagged

  Risk: LOWMar 15, 2026Full report

• ZeroLeaks

  warn

  1 finding · Score: 69/100

  Risk: MEDIUMApr 16, 2026Full report