The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the @membranehq/cli tool from the npm registry. This package belongs to the vendor and is used to manage integration logic.
[COMMAND_EXECUTION]: The skill provides instructions to execute various membrane CLI commands for logging in, connecting to Wrike, and running actions. These are necessary for the skill's primary function and authentication flow.
[PROMPT_INJECTION]: The skill interacts with external data from Wrike, creating a potential surface for indirect prompt injection.
Ingestion points: Data is retrieved via list-comments, list-tasks, and get-task (SKILL.md).
Boundary markers: No specific delimiters are provided to isolate untrusted Wrike content from agent instructions.
Capability inventory: The skill can execute actions via membrane action run and arbitrary API requests via membrane request (SKILL.md).
Sanitization: No explicit content sanitization or validation is mentioned in the prompt instructions.
[SAFE]: No malicious patterns such as obfuscation, credential theft, or unauthorized persistence were identified. The use of a managed CLI for authentication follows security best practices by avoiding local storage of secrets.

wrike