skills/xmcp-dev/skills/prompt-design/Gen Agent Trust Hub

prompt-design

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied data through an interactive workflow to generate TypeScript source files.
  • Ingestion points: User responses to questions about prompt names, parameter descriptions, and use cases as defined in SKILL.md.
  • Capability: Writing generated code to the src/prompts/ directory.
  • Boundary markers: The skill does not explicitly define delimiters for untrusted user input during the code generation phase.
  • Sanitization: There are no specific instructions for escaping or validating user-provided strings before they are interpolated into the generated code templates.
  • [DYNAMIC_EXECUTION]: The skill generates executable TypeScript files based on user input and predefined templates found in references/patterns.md. This is the primary intended function of the skill for developer productivity.
  • [COMMAND_EXECUTION]: The skill instructs the agent to suggest running pnpm build to the user. This is a standard build command used in Node.js environments to verify compilation.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 04:51 AM