The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructions in README.md specify installing the @discountry/clickup-cli package and adding the skill from the author's GitHub repository. These are documented as vendor-owned resources.
[COMMAND_EXECUTION]: The skill operates by executing system commands through the global clickup CLI as described in SKILL.md.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its interaction with external content from ClickUp.
Ingestion points: The agent processes external data when reading task details, comments, and documents through commands such as get, comments, doc, and page (SKILL.md).
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the logic to protect the agent from malicious content within ClickUp data.
Capability inventory: The skill possesses significant write capabilities, including posting comments (comment), creating tasks (create), and editing page content (edit-page), which could be misused if the agent is manipulated (SKILL.md).
Sanitization: No explicit sanitization or validation of the external content is performed before it is added to the agent's context.

clickup