cybersource
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@membranehq/clipackage via the npm registry. This is the official command-line interface provided by the vendor to manage integrations. - [COMMAND_EXECUTION]: The skill utilizes shell commands through the
membraneCLI to handle authentication (membrane login), connection management (membrane connection ensure), and API interaction (membrane action run). These are standard operations for the tool's intended use. - [INDIRECT_PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by retrieving data from external CyberSource API endpoints.
- Ingestion points: Data is brought into the agent's context through output from
membrane action runandmembrane requestcalls. - Boundary markers: The instructions do not specify any delimiters or safety markers to isolate API data from the agent's instructions.
- Capability inventory: The skill's environment includes capabilities for network requests, package installation, and local credential management via the CLI.
- Sanitization: There is no explicit mention of sanitizing or validating the contents of the API responses before they are processed by the agent.
Audit Metadata