matrixscan-ar-net-maui
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill contains instructions directing the agent to prioritize provided reference material over internal training data and to provide information directly rather than referring the user to external documentation. These are grounding instructions intended to ensure technical accuracy regarding SDK versions and APIs, and are not attempts to bypass safety filters.
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch version information from the official NuGet gallery (nuget.org). NuGet is a well-known and trusted service for package management in the .NET ecosystem. This operation is used solely to ensure the correct SDK version is pinned in the user's project files.
- [DATA_EXFILTRATION]: No sensitive file paths or credential harvesting patterns were found. The skill includes placeholders for license keys and instructs users on best practices for managing them. Network requests are limited to trusted documentation and package registry domains.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources to determine SDK versions, creating a theoretical surface for indirect injection.
- Ingestion points: SKILL.md and integration.md instruct the agent to fetch the latest version from nuget.org.
- Boundary markers: None are specified for the fetched content.
- Capability inventory: The agent utilizes WebFetch to read page content and then modifies project files based on this data.
- Sanitization: No explicit sanitization of the fetched version string is performed before it is suggested for use in code.
Audit Metadata