cyberark

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Installs the vendor-provided @membranehq/cli package from the npm registry to interact with the Membrane platform.\n- [COMMAND_EXECUTION]: Uses the membrane CLI to perform authentication, discover actions, and execute API requests against CyberArk.\n- [PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection because it processes data fetched from external CyberArk API endpoints (such as activity records or group names) which could contain adversarial content.\n
  • Ingestion points: Data returned from membrane action run and membrane request commands (SKILL.md).\n
  • Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the data ingestion process.\n
  • Capability inventory: The skill allows the agent to execute write actions and proxy requests to the CyberArk API via the CLI.\n
  • Sanitization: Relies on the structured nature of the JSON responses without additional validation or sanitization layers described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 03:04 PM