The skill risks arbitrary code execution via unsanitized
Claims to do
Zoho Mail: Access the Zoho Mail API with managed OAuth authentication. Send, receive, search, and manage emails with full folder and label management.
Actually does
This skill executes Python scripts to make HTTP requests to `https://gateway.maton.ai` and `https://ctrl.maton.ai`. It uses the `MATON_API_KEY` environment variable for authentication. The `gateway.maton.ai` endpoint acts as a proxy to the `mail.zoho.com` API, handling Zoho Mail OAuth tokens internally, while `ctrl.maton.ai` manages these OAuth connections.
openclaw skills install byungkyu/zoho-mailThe skill content heavily relies on `python <<'EOF' ... EOF` blocks for demonstrating API calls. If an agent's input is not properly sanitized before being used to construct or execute these commands, it could lead to arbitrary code execution within the agent's environment.
```bash
python <<'EOF'
import urllib.request, os, json
req = urllib.request.Request('https://gateway.maton.ai/zoho-mail/api/accounts')
req.add_header('Authorization', f'Bearer {os.environ["MATON_API_KEY"]}')
print(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))
EOF
```The stated purpose implies direct access to the Zoho Mail API with managed OAuth. However, the skill actually proxies all requests through a third-party Maton gateway, requiring a Maton API key and relying on Maton's infrastructure to manage the Zoho Mail OAuth authentication.
Base URL: `https://gateway.maton.ai/zoho-mail/{native-api-path}`. The gateway proxies requests to `mail.zoho.com` and automatically injects your OAuth token. All requests require the Maton API key in the Authorization header.[](https://mondoo.com/ai-agent-security/skills/clawhub/byungkyu/zoho-mail)<a href="https://mondoo.com/ai-agent-security/skills/clawhub/byungkyu/zoho-mail"><img src="https://mondoo.com/ai-agent-security/api/badge/clawhub/byungkyu/zoho-mail.svg" alt="Mondoo Skill Check" /></a>https://mondoo.com/ai-agent-security/api/badge/clawhub/byungkyu/zoho-mail.svgSkills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.