ikigai

Pass

Audited by Gen Agent Trust Hub on Oct 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli NPM package. This is an official vendor-provided tool for managing connections and actions within the Membrane ecosystem.
  • [INDIRECT_PROMPT_INJECTION]: The skill handles data from the external Ikigai API, which represents a potential attack surface for indirect prompt injection.
  • Ingestion points: Data returned from external actions and API requests via membrane action run and membrane request in SKILL.md.
  • Boundary markers: None are explicitly defined in the provided instructions to separate external data from the agent prompt.
  • Capability inventory: The skill is capable of executing membrane CLI commands and performing proxied network operations.
  • Sanitization: The skill follows best practices by recommending pre-built actions which utilize structured data, providing safer interaction compared to raw API calls.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 16, 2026, 07:38 AM