The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the official NPM registry. This is a vendor-owned resource required for the skill to communicate with the Membrane platform.
[COMMAND_EXECUTION]: Uses the membrane CLI for managing the integration lifecycle, including authentication (membrane login), connection setup (membrane connect), and action execution (membrane action run). These commands are standard for the platform's operation.
[REMOTE_CODE_EXECUTION]: Triggered via the membrane action run and membrane action create commands. These operations execute logic within the Membrane platform's managed environment, which is the intended design for this integration.
[DATA_EXFILTRATION]: Facilitates the transfer of email marketing data between the agent's environment and the AcyMailing service. The skill follows best practices by letting the platform manage credentials server-side, preventing the exposure of API keys in local scripts or prompts.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes data retrieved from AcyMailing (e.g., campaign content, mailing lists).
Ingestion points: Data enters the context via membrane action run and membrane action list when fetching records from AcyMailing.
Boundary markers: None are explicitly defined in the instruction set to delimit untrusted data.
Capability inventory: The skill can execute network and data operations through the membrane tool.
Sanitization: No specific sanitization or filtering of external data is described in the provided markdown instructions.

acymailing