The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @membranehq/cli package from the npm registry. This is a vendor-owned resource for 'membranedev' used to facilitate the integration.
[COMMAND_EXECUTION]: The skill utilizes the membrane CLI to perform API actions and proxy requests. These commands are specific to the skill's functionality for managing agreements and users.
[CREDENTIALS_UNSAFE]: No hardcoded credentials or secrets were detected. The skill correctly utilizes the membrane login and membrane connect commands, which delegate authentication to the platform and keep tokens out of the local environment.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it retrieves and processes external document information from Adobe Acrobat Sign.
Ingestion points: Untrusted data enters the context through actions like list-agreements, get-agreement-form-data, and generic API requests via membrane request.
Boundary markers: There are no explicit markers or instructions provided to the agent to treat retrieved document content as untrusted data.
Capability inventory: The agent has the capability to execute subprocesses (via the membrane CLI) and perform further network operations (via the proxy functionality).
Sanitization: The documentation does not describe any sanitization or validation of the data retrieved from the Adobe Acrobat Sign API before it is processed by the agent.

adobe-acrobat-sign