automate-whatsapp

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The openapi-explore.mjs script fetches OpenAPI specifications from docs.kapso.ai. This is a vendor-owned domain used for documentation and is considered a safe source for configuration data.
  • [REMOTE_CODE_EXECUTION]: The skill facilitates the creation and deployment of JavaScript functions to the Kapso platform via create-function.js and update-function.js. While this involves executing code on a remote server, it is the primary intended functionality of the skill for workflow automation and occurs within the user's authenticated platform environment.
  • [CREDENTIALS_UNSAFE]: The skill requires KAPSO_API_KEY and GitHub PATs for repository access. It correctly instructs the user to manage these sensitive credentials via environment variables or configuration files rather than hardcoding them within the scripts or instructions.
  • [DATA_EXFILTRATION]: The skill performs network operations using fetch to interact with the Kapso API (KAPSO_API_BASE_URL). These operations are restricted to the configured base URL and are necessary for the skill's purpose of managing workflows and database rows.
  • [COMMAND_EXECUTION]: The skill provides a series of Node.js scripts to interact with the Platform API. These scripts are invoked via standard CLI patterns and do not involve the execution of arbitrary shell commands from untrusted inputs.
  • [DYNAMIC_EXECUTION]: The 'Agent Remote Sandbox' feature allows for the cloning of GitHub repositories into an ephemeral workspace. The skill provides clear guidelines on mounting paths and network policies (allow_list vs allow_all) to manage the security of these temporary environments.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 01:05 AM