ClawHub
Back to skill

Security audit

Email Reader

Security checks for vulnerabilities and agentic risk

Overview

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.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
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.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
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.

External Transmission

Medium
Category
Data Exfiltration
Content
## 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:
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.