phoenix-cli — 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

  pass

  This skill is a developer tool from Arize AI that enables agents to interact with the Phoenix observability platform for LLM application debugging. It uses the official vendor CLI to fetch and annotate traces. The primary security risk is indirect prompt injection, as the skill requires the agent to analyze untrusted trace data (LLM inputs and outputs) which could contain adversarial instructions designed to influence the agent's actions during the review process.

  Risk: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTIONMay 13, 2026Full report

• Socket

  pass

  No alerts

  May 13, 2026Full report

• Snyk

  fail

  Risk: HIGH · 2 issues

  Risk: HIGHMay 13, 2026Full report

• Runlayer

  warn

  1/1 file flagged

  Risk: MEDIUMFeb 28, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report