adyen
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@membranehq/clipackage via npm. This is a legitimate tool provided by the author (membranedev) to facilitate communication between the agent and the Membrane platform. - [INDIRECT_PROMPT_INJECTION]: The skill facilitates data ingestion from the Adyen API, which constitutes a potential surface for indirect prompt injection.
- Ingestion points: Data is retrieved from Adyen via the
membrane action runandmembrane requestcommands as described inSKILL.md. - Boundary markers: The instructions do not implement specific delimiters or safety prompts to isolate external data from the agent's instructions.
- Capability inventory: The skill utilizes the
membraneCLI to perform authenticated network operations and manage API interactions. - Sanitization: There are no explicit instructions for sanitizing or validating the data returned from the Adyen API.
Audit Metadata