clickup
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires installation of the
@krodak/clickup-cliNPM package and a Homebrew tap fromkrodak/tap. These are official vendor-owned resources necessary for the tool's operation. - [COMMAND_EXECUTION]: The skill makes frequent use of the
cupCLI tool to interact with the ClickUp service, which requires executing shell commands. - [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from the ClickUp API, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: Task descriptions, comments, and activity logs retrieved via
cup task,cup activity, andcup commentsas described inSKILL.md. - Boundary markers: There are no specified delimiters or instructions in the skill to distinguish between external data and agent instructions.
- Capability inventory: The skill possesses network access via the ClickUp API, file system access through commands like
cup exportandcup attach, and command execution capabilities viacup. - Sanitization: The skill documentation does not mention any sanitization or validation of content fetched from the ClickUp API.
Audit Metadata