matrixscan-ar-cordova
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a legitimate development tool for the Scandit MatrixScan AR SDK. It contains no malicious code, obfuscation, or data exfiltration patterns.\n- [CREDENTIALS_UNSAFE]: The skill correctly uses placeholder strings for sensitive data such as license keys (e.g., '-- ENTER YOUR SCANDIT LICENSE KEY HERE --') in all provided code examples and fixtures.\n- [EXTERNAL_DOWNLOADS]: All external links and documentation references point to official Scandit domains (scandit.com) or their official GitHub repositories. These references are used for providing authoritative API documentation and samples.\n- [COMMAND_EXECUTION]: The skill instructs the agent to use file-editing tools to modify user source code for SDK integration. This is the primary intended function of the skill and is carried out using standard templates and reference guides.\n- [PROMPT_INJECTION]: The skill uses instructional language to guide the agent toward accurate and helpful responses. These instructions do not attempt to bypass safety guidelines or conceal malicious intent. The skill possesses an indirect prompt injection surface as it ingests and modifies user code, which is the core purpose of the tool.\n
- Ingestion points: User project files (e.g., index.js, IntegratedApp.js).\n
- Boundary markers: Absent.\n
- Capability inventory: File-writing access to the user's project directory via standard agent tools.\n
- Sanitization: Absent; the skill relies on pre-defined reference templates for its code generation tasks.
Audit Metadata