label-capture-net-maui
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the capture of data from physical labels (barcodes and text), which serves as an ingestion point for untrusted external input. This represents an indirect prompt injection attack surface if the extracted data is subsequently passed to an LLM without proper sanitization.
- Ingestion points: CapturedLabel fields including Barcode.Data and Text values.
- Boundary markers: The instructions do not define delimiters or markers for wrapping captured data during processing.
- Capability inventory: The skill documents data extraction and display; no instructions for command execution or unsafe file operations using captured data are present.
- Sanitization: No sanitization or validation logic is provided in the integration examples.
- [EXTERNAL_DOWNLOADS]: The skill references the official NuGet package repository for SDK dependencies, which is a well-known and trusted service.
- [CREDENTIALS_SAFE]: The skill includes explicit instructions for the secure handling of license keys, advising the agent to use dedicated MCP tools and mask secrets in the user interface to prevent leakage.
Audit Metadata