imaging-data-commons — 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 facilitates access to the National Cancer Institute's Imaging Data Commons (IDC) for medical imaging research. It includes instructions for the AI agent to automatically upgrade the primary 'idc-index' Python package using shell commands at runtime, which modifies the system's execution environment. Additionally, the skill processes large-scale metadata from external databases, posing a surface for indirect prompt injection. While these operations are functional requirements for scientific data access, they represent significant security considerations for autonomous agents.

  Risk: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTIONApr 11, 2026Full report

• Socket

  pass

  No alerts

  Apr 11, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · 1 issue

  Risk: MEDIUMApr 11, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 15, 2026Full report