ClickUp Automation
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses templates to automate workflows based on data from ClickUp and external integrations like GitHub. This data is interpolated into instructions without sufficient isolation.
- Ingestion points: Untrusted data enters the agent context through task details, space configurations, automation rules, and external integration data (e.g., branch names, PR URLs) as defined in SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions to the agent to ignore potentially malicious content embedded in the processed data.
- Capability inventory: The skill utilizes tools for managing tasks, lists, spaces, and automations (clickup_task, clickup_list, clickup_space, clickup_automation) which involve writing data to external APIs.
- Sanitization: The instructions do not specify any validation, escaping, or filtering of the external data before it is used in templates.
Audit Metadata