commandkit-plugin-development
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the processing of external source code and command arguments through plugin hooks, creating a surface for indirect prompt injection.
- Ingestion points: The transform method in references/03-compiler-plugin-transform.md accepts raw source code (params.contents), and the registerTemplate callback in references/04-template-registration.md accepts external arguments (args).
- Boundary markers: No specific delimiters or safety instructions are provided to isolate untrusted data during transformation or generation.
- Capability inventory: The skill demonstrates the ability to write files to the filesystem using node:fs/promises's writeFile within the template registration logic (references/04-template-registration.md).
- Sanitization: Examples show direct interpolation of input strings into generated code templates without sanitization or validation.
- [DYNAMIC_EXECUTION]: The skill includes patterns for generating executable script files.
- Pattern description: The references/04-template-registration.md file provides an example of a plugin that generates .ts files based on user-provided templates.
- Evidence: The tools/ directory contains Node.js scripts that print boilerplate code for new plugins.
Audit Metadata