spiritme

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the npm registry. This is an official tool provided by the vendor for managing integrations and authentication.
  • [COMMAND_EXECUTION]: The instructions utilize the membrane CLI to perform authenticated actions, search for integration capabilities, and interact with the SpiritMe API.
  • [INDIRECT_PROMPT_INJECTION]: The agent may process data returned from the SpiritMe API. While all external data processing carries a baseline risk of indirect prompt injection, the skill's structure relies on Membrane's managed environment for secure communication.
  • Ingestion points: SpiritMe API responses via membrane request or membrane action run commands.
  • Boundary markers: None explicitly defined in the skill text.
  • Capability inventory: Network requests, action execution, and connection management via the membrane CLI as documented in SKILL.md.
  • Sanitization: Credential management and request formatting are handled by the Membrane platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 08:48 AM
Security Audit — agent-trust-hub — spiritme