quipu

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs the installation of the @membranehq/cli tool via npm. This package is the official interface for the Membrane platform and is a trusted vendor resource for this integration.
  • [COMMAND_EXECUTION]: The skill uses the membrane command-line interface to perform all integration tasks, such as logging into the platform, listing connections, and running financial actions. These commands are integral to the skill's functionality.
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection by using user-provided strings in its CLI commands.
  • Ingestion points: User-defined intents and JSON parameters are passed directly to the membrane action list and membrane action run commands.
  • Boundary markers: There are no delimiters or specific instructions to the agent to treat this data as untrusted.
  • Capability inventory: The skill provides the ability to manage accounts, transactions, and contacts on the Quipu platform.
  • Sanitization: No sanitization or validation of the user-provided input is specified before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 04:41 PM
Security Audit — agent-trust-hub — quipu