skills/xmcp-dev/skills/create-tool/Gen Agent Trust Hub

create-tool

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill functions as a code generator that interpolates user-provided information into TypeScript and React templates to create new files.
  • Ingestion points: The interactive workflow in SKILL.md (Step 1) collects user input for tool names, parameter descriptions, and validation rules.
  • Boundary markers: No specific delimiters or safety instructions are implemented to isolate user-provided text from the code templates.
  • Capability inventory: The skill allows the agent to write new files to the src/tools/ directory.
  • Sanitization: There are no instructions for sanitizing or escaping the user's input before it is placed into the generated source code.
  • [COMMAND_EXECUTION]: The skill prompts the execution of local shell commands to verify the generated code.
  • Evidence: SKILL.md instructs the user to run pnpm build after the tool has been generated.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 04:51 AM