bitwarden

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the Membrane CLI via npm install -g @membranehq/cli@latest. This is an official package from the skill's vendor and is used for the primary functionality of the skill.
  • [COMMAND_EXECUTION]: The skill uses the membrane CLI to perform operations like login, connection management, and action execution. These are standard operations for this integration.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes untrusted data from Bitwarden and has capabilities to execute further actions.
  • Ingestion points: Data returned from membrane action run (vault items, notes, etc.) enters the agent context (SKILL.md).
  • Boundary markers: None identified in the prompt instructions to distinguish external data from system instructions.
  • Capability inventory: The skill can list actions, create new actions, and run arbitrary actions via the Membrane CLI (SKILL.md).
  • Sanitization: No explicit sanitization or validation of the content retrieved from Bitwarden is mentioned before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 10:02 AM