barcode-selection-kmp

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides integration instructions and code samples for the Scandit Barcode Selection SDK. All referenced dependencies (Maven artifacts under com.scandit.datacapture.kmp and the GitHub repository Scandit/datacapture-kmp-spm) are official vendor resources belonging to the author, 'scandit'.
  • [PROMPT_INJECTION]: The skill contains instructions to 'Do Not Trust Internal Knowledge' and 'Always verify APIs'. These are standard grounding techniques to prevent the LLM from using outdated or incorrect training data for a specific SDK version (8.6), rather than attempts to bypass safety filters.
  • [DATA_EXPOSURE]: The skill includes specific instructions to protect sensitive data, such as masking license key previews in chat and explicitly forbidding the agent from searching the local environment or project files for existing keys. These are security best practices.
  • [REMOTE_CODE_EXECUTION]: No remote code execution patterns were found. The skill uses standard package managers (Gradle and Swift Package Manager) for library management, and all sources are vendor-controlled.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 10:57 PM