skills/ruvnet/ruflo/migrate-create/Gen Agent Trust Hub

migrate-create

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The documentation references npx @claude-flow/cli@latest, which fetches the vendor's command-line interface from the NPM registry.
  • [REMOTE_CODE_EXECUTION]: The use of npx is suggested for executing vendor-provided tools from a remote registry, which is consistent with the skill's intended development workflow.
  • [COMMAND_EXECUTION]: The skill includes shell command examples for manual interaction with the migration memory store.
  • [PROMPT_INJECTION]: The skill has an indirect injection surface where user-supplied migration names and external memory search results are used to generate SQL file content.
  • Ingestion points: The argument and output from the agentdb_pattern-search tool.
  • Boundary markers: None.
  • Capability inventory: File writing, globbing, and bash execution via allowed tools.
  • Sanitization: Not explicitly implemented in the provided templates.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 03:18 PM
Security Audit — agent-trust-hub — migrate-create