structurizr

Pass

Audited by Gen Agent Trust Hub on Oct 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the Membrane CLI (@membranehq/cli) globally via npm. This is a standard setup for the vendor's official management tool used to facilitate authentication and API interaction.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from Structurizr (models, containers, components, and documentation), which could contain adversarial instructions if the workspace content is untrusted.
  • Ingestion points: Workspace data fetched from structurizr.com via actions or proxy requests.
  • Boundary markers: No specific delimiters or safety instructions are provided to the agent for handling data retrieved from the API.
  • Capability inventory: The agent can execute workspace actions and perform network requests (GET, POST, etc.) via the membrane request command.
  • Sanitization: No explicit validation or filtering logic for external data is documented in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 4, 2026, 04:36 PM