ClawHub
Back to skill

Security audit

NetEase Enterprise Mail

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for managing NetEase Enterprise Mail, but its fallback setup tells the agent to run remote installer scripts directly in a shell without verification or clear user approval.

Before installing, review or verify the OOMOL CLI installer through a trusted channel and do not let an agent run the remote install commands automatically. Once the CLI is already installed and authenticated, the mail actions are clearly disclosed, but sending, moving, or deleting mail should require explicit confirmation of the exact target and payload.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The skill instructs the agent to install software by piping a remotely fetched script directly into a shell (curl ... | bash). This creates a supply-chain and remote-code-execution risk: if the install endpoint, transport, or hosting account is compromised, arbitrary code would run immediately on the host without inspection.

Content

Scanner excerpt · SKILL.md (reported line 66)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description says to use this skill for "ANY NetEase Enterprise Mail request" and "Whenever a task involves NetEase Enterprise Mail," which is an extremely broad invocation condition. It lacks scope boundaries, exclusions, or negative examples, so ordinary mentions of NetEase Enterprise Mail could trigger the skill unintentionally.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.