create-plugin

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to create the plugin's directory structure and generates a smoke.sh script intended for local verification. This behavior is consistent with the skill's primary purpose of code generation and development automation.
  • [DATA_EXFILTRATION]: No exfiltration patterns were detected. The listed mcp__claude-flow__transfer_* tools are used for searching and retrieving metadata related to plugin registration and marketplace availability within the vendor ecosystem.
  • [INDIRECT_PROMPT_INJECTION]: As a scaffolding tool, the skill interpolates user-supplied strings (such as plugin names and descriptions) into generated Markdown and YAML frontmatter. This represents a standard surface for indirect prompt injection; however, it is functionally required for the task and does not elevate the risk level for this specific use case.
  • [SAFE]: The skill's operations are transparently described and limited to scaffolding a project structure using authorized platform tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 01:22 PM
Security Audit — agent-trust-hub — create-plugin