The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package from the NPM registry. This is the official tool provided by the vendor for managing integrations and is a standard dependency for the skill's functionality.
[COMMAND_EXECUTION]: Uses shell commands through the membrane CLI to perform actions such as logging in, connecting to services, and running payment-related queries. These operations are scoped to the intended functionality of the payment gateway integration.
[CREDENTIALS_UNSAFE]: The skill explicitly follows best practices by instructing the agent to never ask the user for API keys or tokens, instead relying on Membrane's server-side connection management to handle the authentication lifecycle securely.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes data from external transactions and payment records.
Ingestion points: Data enters the context via the output of membrane action run in the SKILL.md workflow.
Boundary markers: No specific boundary markers or 'ignore' instructions are used when processing external transaction data.
Capability inventory: The agent has the capability to execute shell commands via the membrane CLI and manage connections.
Sanitization: There is no evidence of sanitization or schema validation performed on the raw output from external actions before it is consumed by the agent.

aci-payon