xendit
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from Xendit, such as invoices, payouts, and balance information, which could potentially contain untrusted content.
- Ingestion points: Data retrieved from Xendit via actions or proxy requests in
SKILL.md. - Boundary markers: Not explicitly defined in the provided instructions.
- Capability inventory: Includes the ability to execute actions, manage connections, and send network requests through the Membrane proxy.
- Sanitization: Relies on the agent's handling of structured JSON output from the CLI.
- [SAFE]: The skill installs the
@membranehq/clipackage, which is the official command-line interface provided by the skill's author (membranedev). This is standard functionality for the integration.
Audit Metadata