wrike-automation

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly requires calling Rube MCP Wrike tools (e.g., WRIKE_GET_FOLDERS, WRIKE_GET_ALL_CUSTOM_FIELDS, WRIKE_GET_TASK_BY_ID) to fetch user-created folder names, task descriptions, contacts and custom fields from a Wrike workspace — untrusted, user-generated content that the agent reads and uses to choose IDs and drive subsequent actions (folder selection, task creation), which could enable indirect prompt injection.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill requires adding and using the MCP endpoint https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS) to fetch current tool schemas that directly control the agent's available instructions and behavior, making this external URL a required runtime dependency that influences prompts.