clickup
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONREMOTE_CODE_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill documentation instructs users to install a CLI tool from a public registry.
- Package:
@discountry/clickup-cliis installed globally vianpm installand used by the agent to interact with the ClickUp API. - Reference: The skill also mentions adding itself via a GitHub URL (
https://github.com/discountry/clickup-cli). These are documented vendor resources from the skill's author.
- Package:
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external ClickUp tasks and documents, which could potentially harbor hidden instructions designed to influence the agent's behavior.
- Ingestion points:
SKILL.mdcontains commands to read task data, comments, and document content (clickup get,clickup comments,clickup doc,clickup page). - Boundary markers: Absent. There are no explicit instructions or delimiters defined to separate user-provided ClickUp content from the agent's instructions.
- Capability inventory:
SKILL.mdidentifies several write capabilities, including task creation, comment addition, and document editing (clickup create,clickup comment,clickup edit-page). - Sanitization: Absent. The skill does not specify any sanitization or validation of the retrieved content before it enters the agent's context.
- Ingestion points:
Audit Metadata