cueframe-component-authoring

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill utilizes the cueframe CLI package via npx -y cueframe@0.12. This is an official vendor tool used for scaffolding and synchronizing component source code.\n- [REMOTE_CODE_EXECUTION]: Uses npx to download and execute the cueframe CLI tool from the npm registry. This is the standard method for using the vendor's development utilities.\n- [COMMAND_EXECUTION]: Instructions provide for executing various CLI commands (init, new, push, sync, render) to manage local project workspaces. These operations are essential to the developer workflow documented in references/native-component-workflows.md.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external component definitions and source code, creating a potential attack surface for indirect prompt injection. \n
  • Ingestion points: Component data is ingested via list_catalog and get_component_source.\n
  • Boundary markers: The instructions mandate preserving exact scoped identities and validating documentSha256 hashes.\n
  • Capability inventory: Uses tools to write code to the platform and executes local CLI commands.\n
  • Sanitization: Employs a linter and strict source contract to refuse dangerous code like eval() or fetch() within authored components.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 02:14 PM