Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Clickup Task
v1.0.0Create tasks in Vision Play ClickUp lists (visionplay or inbox).
⭐ 0· 79·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
Name and description align with required items: bash/curl and CLICKUP_TOKEN plus two ClickUp list IDs are expected for creating ClickUp tasks.
Instruction Scope
The SKILL.md tells the agent to execute /usr/local/bin/clickup_create_task.sh with user-provided arguments. The script itself is not included, so its behavior cannot be audited. The instructions also don't require explicit validation or escaping of user inputs (title/description), which creates a risk of shell/command injection or unexpected side effects from the underlying script.
Install Mechanism
This is instruction-only with no install spec (low install risk). However, it depends on a pre-existing binary at /usr/local/bin/clickup_create_task.sh that the bundle does not install or disclose, which is unusual and prevents review of what will actually run.
Credentials
Requested environment variables (CLICKUP_TOKEN and two CLICKUP_LIST_* IDs) are proportionate to the described task-creation use case. No unrelated secrets are requested.
Persistence & Privilege
always is false and the skill has no install/persistence behavior. It does allow normal autonomous invocation (platform default) but does not request elevated persistent privileges.
What to consider before installing
This skill appears to do what it says (create ClickUp tasks) and only asks for a ClickUp token and list IDs, but the actual work is delegated to a server script (/usr/local/bin/clickup_create_task.sh) that is not included for review. Before installing or enabling this skill: 1) inspect the script at /usr/local/bin/clickup_create_task.sh to confirm it only calls the ClickUp API and does not read or transmit other data; 2) ensure the agent will properly escape or validate user-supplied title/description to prevent shell injection; 3) use a ClickUp token with minimal scope (dedicated service account or limited permissions) in case the script is compromised; and 4) if you cannot review the script, consider rejecting or requesting the skill author provide the script source or embed the minimal HTTP-curl logic in the skill bundle for auditability.Like a lobster shell, security has layers — review code before you run it.
latestvk978kbewkxak40n7yw3nt0bj2x83jdz7
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
Binsbash, curl
EnvCLICKUP_TOKEN, CLICKUP_LIST_VISIONPLAY, CLICKUP_LIST_INBOX