The Agent Skills Directory

[Indirect Prompt Injection] (HIGH): The skill is designed to process untrusted user input to generate or modify code while possessing high-privilege capabilities.
Ingestion points: Untrusted data enters the context via user requests and triggers such as "Help me with nestjs module generator".
Boundary markers: None. The skill does not define any delimiters or instructions to treat user data as untrusted.
Capability inventory: The skill is granted Bash, Write, and Edit tools, allowing for system-level changes and command execution.
Sanitization: Absent. There is no logic provided to validate or escape inputs before they are used in the generation process.
[Command Execution] (HIGH): The inclusion of the Bash tool in allowed-tools represents a significant security risk when paired with generative tasks. Without strict constraints, the agent may be coerced into executing destructive shell commands hidden within a module generation request.

nestjs-module-generator