Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward read-only Monday.com helper that uses the user's Monday API token to fetch boards, items, workspaces, and users from Monday's own API.
Install this only if you are comfortable giving the skill a Monday.com API token with access to the boards and user information available to that token. Prefer a least-privileged token or account where possible, and avoid running commands against workspaces containing data you do not want printed in the agent session.
The skill requires an environment secret (MONDAY_API_TOKEN) and performs direct network access to api.monday.com, but it does not declare any explicit tool scope such as permissions or allowed-tools. That creates a least-privilege and review gap: an agent/runtime may permit broader capability use than intended, making secret-backed network operations harder to constrain or audit.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
import sys
import urllib.request
BASE_URL = "https://api.monday.com/v2"
API_VERSION = "2024-04"
The script sends GraphQL requests to monday.com's API and retrieves potentially sensitive account, user, workspace, board, and item data, but there is no user-facing disclosure in the CLI output, comments, or docstrings warning that remote network transmission occurs. While the file header notes direct API access, it does not clearly warn users that invoking commands will transmit workspace data to an external service.
No suspicious patterns detected.