The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the membrane CLI to perform operations such as authentication, searching for connectors, and executing SoftLedger actions. These operations are essential for the integration's functionality and are performed within the vendor's ecosystem.
[EXTERNAL_DOWNLOADS]: The skill documentation describes installing the @membranehq/cli package from the NPM registry. This package is an official tool provided by the vendor to facilitate the integration.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes data from SoftLedger (e.g., audit logs, records, files) and possesses the capability to execute CLI commands based on that data.
Ingestion points: Data retrieved from SoftLedger via membrane action run and membrane request (SKILL.md).
Boundary markers: Absent; the instructions do not specify the use of delimiters for external data.
Capability inventory: Shell command execution via the membrane CLI (SKILL.md).
Sanitization: Absent; there is no mention of filtering or sanitizing external content before processing.
[SAFE]: The integration delegates credential management to the Membrane platform, which ensures that sensitive API keys and tokens are handled server-side rather than being exposed in local environment variables or hardcoded in the skill's instructions.

softledger