nanobanana — 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

  The skill possesses a high-severity vulnerability allowing arbitrary file overwrites and potential data exposure due to a lack of path validation in command-line arguments. It also contains misleading metadata regarding its AI model and lacks prompt sanitization.

  Risk: HIGHCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTIONFeb 16, 2026Full report

• Socket

  pass

  No alerts

  Mar 18, 2026Full report

• Snyk

  pass

  Risk: LOW · No issues

  Risk: LOWFeb 17, 2026Full report

• Runlayer

  pass

  5 files scanned · No issues

  Risk: NONEFeb 26, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report