csharp-developer
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core workflow requires the agent to analyze external project files such as
.csprojand NuGet package configurations. These files represent an ingestion point for untrusted data that could be used to deliver hidden instructions or poison the agent's context during architectural analysis. - Ingestion points: SKILL.md Core Workflow Step 1 ("Review .csproj files, NuGet packages, architecture").
- Boundary markers: None specified; the agent is not instructed to use specific delimiters or treat project metadata as potentially untrusted.
- Capability inventory: The skill generates complex application code, configures authentication logic (JWT), and invokes CLI tools for database migrations (
dotnet ef migrations). - Sanitization: The instructions do not define validation or sanitization steps for the external metadata gathered during the analysis phase.
Audit Metadata