pua-loop — 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 implements an autonomous execution loop that suppresses user oversight and forces the agent to continue tasks until completion, bypassing standard safety refusals. It uses shell commands to manage persistent state files, creating a high-risk environment for unintended actions or data exposure.

  Risk: HIGHPROMPT_INJECTIONCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONApr 18, 2026Full report

• Socket

  pass

  No alerts

  Apr 18, 2026Full report

• Snyk

  pass

  Risk: LOW · No issues

  Risk: LOWApr 18, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report