nano-banana-pro — 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 provides image generation and editing capabilities using the Gemini API. While the core functionality is legitimate, it is susceptible to indirect prompt injection because it processes external image files and has the capability to write to the local filesystem. Additionally, it encourages insecure API key handling via command-line arguments.

  Risk: HIGHPROMPT_INJECTIONCREDENTIALS_UNSAFEFeb 15, 2026Full report

• Socket

  pass

  No alerts

  Mar 18, 2026Full report

• Snyk

  fail

  Risk: HIGH · No issues

  Risk: HIGHFeb 17, 2026Full report

• Runlayer

  pass

  1/2 files flagged

  Risk: LOWFeb 26, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report