open-exchange-rates

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from npm. This is an official vendor-provided tool used to manage authentication and execute integration logic.
  • [COMMAND_EXECUTION]: The skill instructs the user to execute various membrane CLI commands, such as membrane action run and membrane request, which involve subprocess execution to interact with external APIs.
  • [PROMPT_INJECTION]: The skill processes data from the Open Exchange Rates API, creating an attack surface for indirect prompt injection.
  • Ingestion points: Data enters the agent's context from the external API through the membrane action run and membrane request commands.
  • Boundary markers: There are no explicit instructions or delimiters used to isolate external data from the agent's instruction set.
  • Capability inventory: The skill has the capability to run arbitrary CLI commands through the membrane interface.
  • Sanitization: No specific filtering or sanitization steps are documented for the responses received from the external API.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 10:24 PM