template-instantiation
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill triggers several shell-based operations using the
dotnetCLI, includingdotnet newfor project creation,dotnet buildfor compilation and restore,dotnet slnfor solution management, anddotnet addfor project referencing. - [EXTERNAL_DOWNLOADS]: The skill downloads external template packages via
dotnet new install. Additionally, it performs network requests to the NuGet V3 flat-container API to resolve package versions during the centralization process. - [INDIRECT_PROMPT_INJECTION]: The skill analyzes local project files to ensure workspace consistency, which introduces a potential surface where adversarial content in those files could influence the agent's behavior.
- Ingestion points: The skill reads
.csprojfiles,Directory.Packages.props, andglobal.jsonduring the workspace analysis phase (Step 2). - Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the analyzed project files are implemented.
- Capability inventory: The skill has the capability to execute shell commands (
dotnetCLI), modify the local file system, and install new template packages. - Sanitization: No sanitization or filtering is applied to the data retrieved from the workspace project files before it is processed by the agent.
Audit Metadata