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
Risk Level
SAFE
Analyzed
Aug 29, 2026, 04:12 PM
Security Audit — agent-trust-hub — commandkit-plugin-development