The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the official Membrane CLI (@membranehq/cli) from the public NPM registry, which is a standard procedure for this vendor's tooling.
[COMMAND_EXECUTION]: The instructions involve executing membrane CLI commands to manage connections and run actions related to Thai Post. These operations are scoped to the authenticated user's account and the specific integration.
[CREDENTIALS_UNSAFE]: The skill explicitly adheres to security best practices by instructing the agent to never ask the user for API keys or tokens, instead using managed connections for authentication.
[DATA_EXFILTRATION]: While the skill processes external tracking and postal data from Thai Post, it does so through a controlled action-running mechanism.
Ingestion points: Data enters the context via membrane track and search action outputs (SKILL.md).
Boundary markers: Absent.
Capability inventory: Subprocess execution of membrane action run (SKILL.md).
Sanitization: Not explicitly documented in the markdown body, but the use of structured JSON output (--json) provides a layer of schema validation.

thai-post