msbuild-antipatterns
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFE
Full Analysis
- Data Ingestion Surface: The skill is designed to review and audit MSBuild XML files, such as
.csproj,.props, and.targets. While processing external data is a standard functional requirement for this skill, it introduces a surface for indirect prompt injection where malicious instructions could be embedded in XML comments or metadata within a project file. However, the skill includes clear instructions to ground findings in the provided catalog, which serves as a context-limiting measure. - Ingestion Points: The agent reads build-related files including project files, property files, target files, and
.nuspecmanifests. - Capability Inventory: The skill is analysis-focused and does not perform network operations, arbitrary command execution, or file modifications unless explicitly requested by the user.
- Boundary Markers: The skill relies on natural language instructions to separate the review logic from the data being analyzed.
- Sanitization: The skill focuses on structural XML analysis rather than executing content from the files.
Audit Metadata