amilia

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions involve executing the membrane command-line utility to manage connections, discover actions, and perform API requests. This is the intended and primary functionality for interacting with the Membrane ecosystem.\n- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package via npm. This is a vendor-owned package associated with the platform mentioned in the instructions.\n- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it reads and processes data from external Amilia records (e.g., account details, registrations). This is a known risk for data-integration skills but is mitigated by the use of structured platform actions and standard LLM guardrails.\n
  • Ingestion points: Data returned from membrane action run and membrane request commands.\n
  • Boundary markers: None explicitly mentioned in the skill instructions.\n
  • Capability inventory: The skill utilizes subprocess execution of CLI commands and network access via the Membrane proxy.\n
  • Sanitization: Relies on the underlying platform's handling of data and the LLM's safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 07:46 PM