ClawHub
Back to skill

Security audit

禅道CLI

Security checks for vulnerabilities and agentic risk

Overview

This ZenTao CLI skill is coherent and purpose-aligned, with disclosed read/write project-management operations and reasonable user-control guidance.

Before installing, confirm you trust the ZenTao CLI package source and prefer a pinned package version for reproducible installs. Use it only with ZenTao accounts and sites you intend the agent to access, and review delete, bulk update, and status-transition requests carefully because they can change business records.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The description says to use this skill whenever the user wants to operate on ZenTao data, query personal to-dos, or install/configure/troubleshoot zentao-cli. While domain-related, the activation scope is still very broad and does not define clear limits or negative examples for when the skill should not activate, which can lead to unintended invocation across many ordinary support or project-management requests.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The skill recommends one-time execution via npx zentao-cli <参数> without pinning a specific package version. This can cause the agent or user environment to fetch and execute whatever version is current at run time, increasing supply-chain risk and reducing reproducibility if a malicious or compromised release is published.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The entire skill documentation is written in Chinese and does not indicate that language selection is optional or configurable. Under the stated policy, forcing a specific language or locale without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.