mesibo

Pass

Audited by Gen Agent Trust Hub on May 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the official npm registry. This is a trusted vendor resource necessary for the skill's functionality.
  • [COMMAND_EXECUTION]: Shell commands are used to interact with the membrane CLI for managing Mesibo data and actions. These operations are part of the intended integration logic.
  • [CREDENTIALS_UNSAFE]: The instructions encourage secure authentication practices by utilizing the membrane login and membrane connect flows, which manage tokens server-side rather than requiring the user to provide raw API keys.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes data from external Mesibo actions. Ingestion points: External data enters through membrane action run outputs (SKILL.md). Boundary markers: None present in the command examples. Capability inventory: Capability to run CLI commands and create new actions via membrane action create (SKILL.md). Sanitization: Relies on the Membrane platform's internal handling of API responses.
Audit Metadata
Risk Level
SAFE
Analyzed
May 10, 2026, 01:04 AM
Security Audit — agent-trust-hub — mesibo