template-smart-defaults
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user data, including template names and parameter values, which are then used to construct shell commands. This creates a potential vulnerability if the input contains malicious instructions intended to manipulate the command structure.
- Ingestion points: The skill receives "Template short name" and "Parameters already chosen" as primary inputs in SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat user-supplied template names or parameters as literal strings rather than executable instructions.
- Capability inventory: The skill is designed to generate and encourage the execution of
dotnet newcommands, including verification steps usingdotnet new <template> --help. - Sanitization: While the workflow requires verifying parameters against help output, there are no specific instructions for shell escaping or input validation to prevent command injection from the template name or parameter values.
- [COMMAND_EXECUTION]: The primary purpose of the skill is the generation and verification of shell commands for the .NET CLI.
- Evidence: The workflow in SKILL.md specifically directs the agent to construct an "exact single dotnet new command line" and run
--helpto confirm available choices.
Audit Metadata