intlayer-cms

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The documentation instructs users to run various CLI tools such as npx intlayer login, npx intlayer config push, and npx intlayer-editor start for content synchronization and local development.
  • [EXTERNAL_DOWNLOADS]: The skill configures the application to fetch remote dictionaries from the Intlayer CMS infrastructure at https://intlayer.org to support dynamic content updates.
  • [REMOTE_CODE_EXECUTION]: The Live Sync feature involves a server that wraps the application's runtime process (e.g., next start) to stream and apply content updates directly to the running instance.
  • [COMMAND_EXECUTION]: The Visual Editor component can overwrite local source code files (JSON, JS, TS) when users save changes through the editor interface, utilizing a babel transformer to modify the codebase.
  • [PROMPT_INJECTION]: The skill introduces a surface for indirect prompt injection by fetching and displaying untrusted remote content from a CMS.
  • Ingestion points: Remote dictionaries fetched via the Live Sync API (concept_cms.md).
  • Boundary markers: None specified in the documentation or configuration.
  • Capability inventory: File system modification (concept_editor.md) and process wrapping (concept_cms.md).
  • Sanitization: The documentation does not specify sanitization or validation of the fetched remote content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 05:18 AM