winapp-frameworks

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [Indirect Prompt Injection Surface]: The skill provides instructions for the agent to read and process project-specific configuration files, which represents a potential attack surface if the files originate from untrusted sources. (1) Ingestion points: The skill describes processing metadata from .csproj, Package.appxmanifest, and package.json files within the workflows described in SKILL.md. (2) Boundary markers: There are no explicit instructions for using boundary markers or delimiters when interpreting the contents of these files. (3) Capability inventory: The skill uses shell execution capabilities for build and runtime operations, such as dotnet build, winapp run, and npm install. (4) Sanitization: The guidance does not include specific sanitization or validation steps for the content ingested from the project files.
  • [External Resource References]: The skill recommends installing dependencies from the @microsoft npm scope and the official Windows Package Manager (winget). It also links to documentation hosted on Microsoft's GitHub repositories. These are standard, vendor-provided resources and are considered safe for development use.
  • [Command Execution]: The skill guides the user through standard development commands for building and debugging applications. These operations are performed within the scope of the developer's project environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 03:13 PM