deputy

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package from the official npm registry. This is a standard tool required to interact with the Membrane platform.
  • [COMMAND_EXECUTION]: The skill executes various membrane CLI commands to manage connections and run actions. This is the intended operational model for the skill.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes external data from Deputy and user-provided descriptions to create or run actions. * Ingestion points: Data retrieved from Deputy actions (e.g., list-employees) and user-provided intent strings in SKILL.md. * Boundary markers: Not explicitly defined in the instruction set. * Capability inventory: Subprocess calls to the membrane CLI which can perform network operations and data retrieval. * Sanitization: Relies on the underlying Membrane platform's handling of action schemas and inputs.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 10:23 PM
Security Audit — agent-trust-hub — deputy