Security audit
Security checks for vulnerabilities and agentic risk
This skill is a coherent local email-classification helper, but users should understand it can process unread email and start or stop a scheduler through a local backend.
Install this only if you trust the local service running on port 8010 and expect it to have access to your email and job-tracking data. Before using fetch or scheduler commands, confirm the backend’s mailbox permissions, retention policy, and how to stop scheduled checks.
The listed activation phrases are entirely in Chinese, and the skill does not state that other languages are supported or that Chinese is an optional locale. This creates a natural-language policy concern because it imposes a language constraint without documented opt-in or justification.
The skill exposes actions to fetch unread inbox contents and start/stop a scheduler without requiring an explicit user confirmation or presenting a warning about privacy and system impact. Because these operations can access private email data and alter ongoing automation state, a user could trigger sensitive actions without understanding the consequences.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
## Command templates (exec tool + curl)
- Ingest:
- `curl -sS -X POST "http://127.0.0.1:8010/api/email/ingest" -H "Content-Type: application/json" -d '{"sender":"hr@example.com","subject":"面试邀请","body":"请于明天下午参加面试"}'`
- Recent:
- `curl -sS "http://127.0.0.1:8010/api/email/recent?limit=20"`
- Fetch unread:
No suspicious patterns detected.