The Agent Skills Directory

[NO_CODE]: The skill consists exclusively of markdown instructions and metadata, with no local scripts, executables, or code files provided for analysis.- [EXTERNAL_DOWNLOADS]: The skill requires the user to connect to an external MCP server at 'https://rube.app/mcp'. This establishes a dependency on third-party infrastructure that processes all project data and agent context sent to the Wrike toolkit.- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection. Ingestion points: The agent retrieves untrusted task descriptions, folder names, and custom field values from Wrike via tools like 'WRIKE_FETCH_ALL_TASKS' and 'WRIKE_GET_TASK_BY_ID'. Boundary markers: None are defined to separate retrieved data from agent instructions. Capability inventory: The skill includes high-privilege tools such as 'WRIKE_DELETE_SPACE', 'WRIKE_DELETE_FOLDER', and 'WRIKE_CREATE_INVITATION'. Sanitization: There is no evidence of sanitization for incoming Wrike content, which could contain malicious instructions designed to trigger the destructive tools.- [COMMAND_EXECUTION]: The toolkit provides access to powerful administrative actions, including 'WRIKE_DELETE_FOLDER' and 'WRIKE_DELETE_SPACE'. These tools perform irreversible deletions of entire project structures and workspace data, which could be abused if the agent is manipulated via injection.

wrike-automation