typesense

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli global package from NPM, which is the vendor's command-line tool for managing integrations.
  • [COMMAND_EXECUTION]: The skill executes multiple shell commands via the membrane CLI to handle user authentication, establish connections to Typesense, and perform API operations.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection when processing search results or document content from Typesense. Ingestion points: Data enters the context via the output of membrane action run and membrane request commands. Boundary markers: No specific delimiters or instructions to ignore embedded commands are present. Capability inventory: The skill can query and retrieve arbitrary data from Typesense collections. Sanitization: The instructions do not specify any sanitization or validation for the data retrieved from the search engine.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 04:09 PM