sensorkit — security audits

Passed all audits

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 provides documentation and code examples for Apple's SensorKit framework, which allows research apps to access highly sensitive sensor data on iOS and watchOS devices. While it describes a legitimate framework intended for approved research studies, the access to extremely private information—such as keyboard metrics, speech transcriptions, and location history—creates significant data exposure risks and an indirect prompt injection surface if the AI agent processes malicious instructions contained within that sensor data.

  Risk: SAFEPROMPT_INJECTIONDATA_EXFILTRATIONMar 28, 2026Full report

• Socket

  pass

  No alerts

  Mar 28, 2026Full report

• Snyk

  pass

  Risk: LOW · No issues

  Risk: LOWMar 28, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report