clickup-issue-create
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides explicit instructions to identify and remove credentials, tokens, personal data, and signed URLs from content before it is transmitted to the external ClickUp service. This demonstrates a security-conscious design for handling user data.
- [INDIRECT_PROMPT_INJECTION]: The skill acts as a transformer for untrusted user input (chat history or specific prompts). While this presents a surface for indirect prompt injection, the risk is mitigated by the following factors:
- Ingestion points: User input and chat history are processed to generate task metadata (SKILL.md).
- Boundary markers: None explicitly defined in the prompt template, but a strict Markdown schema is enforced.
- Capability inventory: The skill uses the
clickupfyMCP and CLI tools to perform network writes to ClickUp. It does not have access to general shell execution or file system modification tools. - Sanitization: There is a mandatory step to scrub secrets before task creation.
- [COMMAND_EXECUTION]: The skill uses a domain-specific CLI tool (
clickupfy) for task management. These commands are executed within the scope of the agent's environment to interact with the vendor's platform and do not involve arbitrary shell injection or privilege escalation.
Audit Metadata