ClawHub
Back to skill

Security audit

Work Productivity Gog Google Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-style workflow helper with no executable code or hidden data access; its main risk is overly broad automatic activation.

Installers should be aware that this skill may activate on broad productivity or Google-related requests. Review its output when it triggers, and prefer explicit invocation if your agent platform lets you control skill routing.

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 (12)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill description and usage guidance are broad enough to match many common requests involving 'google', 'workspace', 'cli', or generic workflow help, which can cause the skill to be invoked outside its intended scope. Over-broad invocation increases the chance of misrouting user tasks, applying irrelevant instructions, or exposing users to unintended automation guidance in contexts where another skill should handle the request.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger keywords are extremely generic and high-frequency terms, including 'google', 'workspace', 'cli', 'gmail', and 'bug fix', without constraints or disambiguation. In an agent-routing system, this can cause frequent unintended activation, leading to incorrect task handling, policy bypass through misclassification, or workflow confusion when unrelated requests are captured by this skill.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

触发关键词包含非常常见且高频的通用词，如“google”“workspace”“cli”“bug fix”，会使该技能在大量无关请求中被误触发。误触发会把用户带入与真实意图不匹配的工作流，增加错误建议、越权式上下文扩展或对其他更合适技能的路由干扰风险。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger examples are generic enough to match common productivity or help-seeking requests, which can cause the skill to activate outside its intended scope. In an agent ecosystem, broad activation increases the chance of inappropriate routing, unnecessary access to adjacent workflows, and user confusion about what the skill will do.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broad enough to match common productivity or workflow requests that many users might make without intending to invoke this specific skill. That can cause unintended activation, routing user data or actions into the wrong workflow, especially in agent ecosystems where skill selection may be automated from natural-language prompts.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

技能描述将启用条件写成一组宽泛主题和产出类型的并列集合，但没有明确边界说明何时不应触发。这样的模糊性会导致路由器或代理在低置信场景下仍选择本技能，从而扩大不相关上下文摄取和错误操作建议的概率。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

示例触发句使用了“Help me”“I need a practical workflow”这类高度通用表达，却没有提供不会触发的反例来约束范围。结果是实现方可能据此采用过度宽松的匹配逻辑，使技能在普通求助语句中被激活。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The default prompt uses very broad language such as 'help me' and generic workflow/productivity framing, which can overlap with many ordinary user requests. When combined with implicit invocation, this increases the chance the skill is selected in situations outside its intended use, expanding attack surface and creating opportunities for unintended behavior or prompt-context contamination.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill enables allow_implicit_invocation without any visible activation constraints, so the platform may trigger it for loosely related requests the user did not explicitly intend. In a productivity/workflow skill with broad scope, this can cause unintended routing, prompt injection exposure through unrelated conversations, or accidental application of workflow guidance in contexts where it was not requested.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger sentence begins with a very broad phrase ('Help me ...') that can easily appear in ordinary user requests unrelated to this specific skill. In an agent ecosystem, overly generic activation text can cause accidental invocation, routing the wrong skill into sensitive workflows, or creating prompt-selection confusion that degrades safety and reliability.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger uses a generic request form ('I need a practical workflow for ...') without clear activation boundaries, making it likely to match many normal planning or productivity requests. This increases the chance of unintended skill selection, especially because the skill is framed broadly around work-productivity and workflow support rather than a tightly scoped operation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This is a zh-CN user-facing README, but key usage content and all sample trigger phrases are written in English, which can impose a language expectation on users without opt-in. The file does not state that English is optional or provide equivalent Chinese trigger examples.

Content

No source excerpt is available for this finding.