template-smart-defaults
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- Command Construction from User Input: The skill generates a
dotnet newshell command by incorporating template names and parameters provided by the user. If these inputs contain shell-sensitive characters and are not strictly validated, there is a possibility of executing unintended commands. - Indirect Prompt Injection Surface: The skill ingests external data (user-specified parameters) which is then used to determine the logic for applying default values. Without clear boundaries or sanitization, this input could potentially be crafted to manipulate the resulting project configuration or command output.
- Ingestion points: Template short names and parameter values are provided as inputs in
SKILL.md. - Boundary markers: The skill suggests confirming parameters against
dotnet new <template> --help, but does not explicitly define sanitization rules for the command generation. - Capability inventory: The skill instructs the agent to generate and potentially execute shell commands (
dotnet new). - Sanitization: No explicit sanitization or escaping of user-provided strings is described before they are interpolated into the command line.
Audit Metadata