Security audit

Work Productivity Gog Google Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with overly broad activation wording but no code execution, credential access, persistence, or hidden high-impact behavior.

Install only if you want a general workflow helper for Gog-style Google Workspace productivity planning. Be aware it may activate for ordinary Google or CLI requests because its trigger wording is broad, so explicit skill invocation or tighter routing would be preferable.

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: 95% confidence
Finding: The manifest description includes very broad terms like 'google', 'workspace', 'cli', 'workflow', 'artifact', and 'analysis', which can cause the skill to activate for many unrelated user requests. Over-broad routing increases the chance that this skill intercepts prompts outside its intended scope, leading to incorrect tool selection, confused delegation, or unintended handling of sensitive productivity tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keyword list is highly ambiguous: single words like 'google', 'workspace', 'cli', 'gmail', 'calendar', and 'drive' are common across many benign tasks and do not uniquely identify this skill's purpose. In a skill-routing system, such broad triggers can cause frequent misactivation, pulling unrelated requests into this skill and increasing the risk of mishandling user intent or exposing adjacent workflow context unnecessarily.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: 触发关键词包含非常通用的词，如“google”“workspace”“cli”“bug fix”，会与大量普通任务重叠，导致该技能被误触发。误触发后，代理可能在并不适用的上下文中套用该技能流程，造成错误操作、结果偏离用户意图，甚至绕过更合适的专用技能。
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger sentences are broad, natural-language phrases that can match ordinary user requests, increasing the chance the skill is invoked when the user did not specifically intend it. In an agent ecosystem, unintended invocation can route tasks to the wrong workflow, causing overbroad access to productivity tooling, irrelevant actions, or confusion that undermines user consent and safe task scoping.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger sentences are generic enough that the skill may activate for loosely related requests involving productivity, Google, CLI, or bug-fixing, causing unintended invocation. In an agent ecosystem, over-broad activation can route sensitive user tasks into the wrong workflow, increasing the chance of inappropriate actions, data handling, or confusing tool behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger phrases are broad, generic, and closely resemble ordinary user requests, which can cause the skill to activate in situations the user did not explicitly intend. In an agent environment, overbroad activation can route unrelated prompts into this workflow, increasing the chance of unintended actions, misleading outputs, or unsafe use of connected Google Workspace-related capabilities.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The example trigger sentences reinforce vague invocation patterns by repeating broad demand language instead of concrete, bounded scenarios. This trains users or downstream systems to invoke the skill for loosely related requests, weakening scope control and compounding the risk of erroneous activation created by the broad metadata and keyword list.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: 技能描述把适用范围定义为用户提到若干宽泛主题，或‘需要实用流程、产物、检查清单、分析或实现支持’时即可使用，边界过宽且缺少排他条件。这会让调度器难以准确判断激活时机，增加在无关任务中调用该技能的概率。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: 示例触发句高度重复，几乎只是复述需求文本，不能帮助系统区分真实适用场景与相似但无关的请求；同时缺少负面示例，无法约束边界。在基于示例学习或规则匹配的触发体系里，这种设计会放大误匹配风险。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The default prompt uses very broad everyday wording such as work productivity, workflow help, fixing bugs, hardening setup, and practical support, which overlaps with many normal user requests. This makes the skill easier to invoke in contexts the user did not explicitly intend, potentially causing over-broad delegation, confusion, or unsafe reliance on a loosely scoped helper.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill enables implicit invocation without any narrowly defined trigger conditions, which can cause the agent to auto-select this skill for broad, ordinary productivity-related requests. Because the skill is framed around common domains like work productivity, Google, workspace, CLI, checklists, and implementation support, this increases the chance of unintended activation and prompt-scope expansion.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: This Chinese README contains substantial English instructional content, including the demand description and trigger phrases, but does not tell users they can choose their preferred language. That can violate language/locale expectations by implicitly forcing part of the interaction into English without opt-in.
Content: No source excerpt is available for this finding.