arangodb

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package, which is the official tool provided by the vendor for managing integrations.
  • [COMMAND_EXECUTION]: The skill uses the membrane CLI to perform authentication, manage connections, and execute database actions.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface due to processing untrusted data from ArangoDB collections.
  • Ingestion points: Data is retrieved from ArangoDB using membrane action run and the membrane request proxy functionality.
  • Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions found within the database content.
  • Capability inventory: The skill can install packages, execute CLI commands, and perform arbitrary HTTP requests via the proxy.
  • Sanitization: No record-level sanitization or schema validation is implemented for the data retrieved from the database.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 08:56 AM