rapyd
Pass
Audited by Gen Agent Trust Hub on Apr 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to install the
@membranehq/clitool from the npm registry, which is the official package provided by the vendor for managing integrations.\n- [COMMAND_EXECUTION]: The skill utilizes shell commands through themembraneCLI to manage connections, discover available actions, and execute API requests against the Rapyd platform.\n- [PROMPT_INJECTION]: The skill acts as an interface for external data from the Rapyd API, creating a surface for indirect prompt injection.\n - Ingestion points: Data returned to the agent from
membrane action runandmembrane requestcommands inSKILL.md.\n - Boundary markers: The instructions do not define specific delimiters for separating API data from agent instructions.\n
- Capability inventory: The skill allows execution of system commands via the
membraneCLI tool.\n - Sanitization: No explicit sanitization of the external API content is documented.
Audit Metadata