clickup-automation

Warn

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires users to add a remote MCP server endpoint (https://rube.app/mcp) to their configuration. Because this endpoint is an unverified third-party service, it introduces a supply chain risk where the remote server could provide malicious tools or code that the agent then executes within its environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from ClickUp tasks and comments, which can be modified by external users to influence agent behavior.
  • Ingestion points: Data enters the agent's context through tools like CLICKUP_GET_TASK, CLICKUP_GET_TASKS, and CLICKUP_GET_TASK_COMMENTS as outlined in the core workflows of SKILL.md.
  • Boundary markers: There are no instructions for using delimiters or explicit warnings to the agent to ignore instructions embedded within the retrieved task content.
  • Capability inventory: The skill exposes powerful capabilities including task creation (CLICKUP_CREATE_TASK), modification (CLICKUP_UPDATE_TASK), deletion (CLICKUP_DELETE_TASK), and commenting (CLICKUP_CREATE_TASK_COMMENT).
  • Sanitization: The instructions do not define any validation or filtering mechanisms to sanitize the content of tasks or comments before they are used to determine subsequent agent actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 6, 2026, 12:16 PM
Security Audit — agent-trust-hub — clickup-automation