agent-memory-mcp — 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

  This skill downloads and executes code from an unverified GitHub repository, which presents a supply chain risk. It also introduces a surface for indirect prompt injection by processing external data without clear boundary markers or sanitization.

  Risk: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTIONApr 13, 2026Full report

• Socket

  pass

  No alerts

  Apr 13, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · 1 issue

  Risk: MEDIUMApr 13, 2026Full report

• Runlayer

  pass

  1 file scanned · No issues

  Risk: NONEFeb 28, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report