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/clipackage 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
membraneCLI commands, such asmembrane action runandmembrane 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 runandmembrane requestcommands. - 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
membraneinterface. - Sanitization: No specific filtering or sanitization steps are documented for the responses received from the external API.
Audit Metadata