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 it does not request privileged access, execute code, persist data, or handle credentials.

Before installing, be aware that this skill may activate too easily for ordinary Google Workspace or productivity requests. It appears safe as a non-executable helper, but the publisher should narrow the triggers or disable implicit invocation to avoid irrelevant use.

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 (11)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill description is broad enough to match common terms like "google," "workspace," and "cli," which can cause the skill to activate for many unrelated requests. Over-broad routing increases the chance that this skill is invoked outside its intended scope, leading to incorrect task handling, prompt collisions with more appropriate skills, and accidental exposure of users to irrelevant workflow guidance.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger keywords include highly generic terms such as "google," "workspace," "cli," "gmail," "calendar," and "drive" without disambiguation or guardrails. This makes unintended invocation very likely across a wide range of unrelated user requests, which is especially risky in agent ecosystems where automatic skill selection may grant the skill influence over tasks it was not designed to handle.
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宽泛且高频的词，如“google”“workspace”“cli”“bug fix”，会让该技能在大量无关请求中被意外激活。误触发会扩大技能适用面，导致错误路由、上下文污染，甚至在涉及 Google Workspace、邮件、日历等敏感业务场景中输出不恰当建议。
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentences are broad, natural-language phrases that can match ordinary user requests far beyond the intended scope of this skill. That raises the risk of unintended activation, causing the agent to invoke this workflow in irrelevant contexts and potentially route user tasks toward the wrong tools, assumptions, or outputs.
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 and generic enough to activate on ordinary user requests about productivity, Google Workspace, or bug fixing, which can cause the skill to run outside its intended scope. Over-broad activation increases the chance of unintended delegation, prompt/context hijacking, and unsafe execution of instructions in contexts the user did not explicitly authorize.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger phrases and keywords are broad, generic, and overlap with common user requests such as 'google', 'workspace', 'cli', and 'help me'. This can cause unintended skill invocation, leading the agent to apply this workflow in unrelated contexts and potentially expose users to incorrect actions, unnecessary tool use, or privilege-bearing workflows they did not intend to run.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: 该文件整体以 SKILL.zh-CN.md 形式面向简体中文语言环境呈现，但未见任何说明用户可选择其他语言，或为何该技能必须限定为 zh-CN。根据规则，强制特定语言而无用户 opt-in 或明确合规理由，属于自然语言层面的语言/区域策略问题。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: 技能描述中的适用条件表述较宽泛，如“当用户提出 work-productivity, gog, google, workspace, cli，或需要围绕该需求获得实用流程……时使用”，缺少清晰边界。这样的模糊激活标准容易让编排器在相似但不相关的任务上调用该技能，降低结果准确性并可能把用户导向不必要的流程或模板。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The default prompt includes the generic phrase 'help me,' which strongly overlaps with ordinary conversational language and can unintentionally match many unrelated user requests. Combined with implicit invocation, this broad phrasing increases the likelihood that the skill is selected when the user did not intend to invoke it, creating routing ambiguity and expanding the skill’s effective attack surface.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: Enabling implicit invocation without narrowly defined trigger constraints can cause the skill to activate in response to broad or unintended user requests. In this skill, that risk is amplified because the functionality is broadly framed around common workplace assistance, which increases the chance of accidental routing, prompt overlap, and unintended execution of the skill’s instructions.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: Although this file is labeled as a Chinese README, substantial descriptive content and trigger text are written in English. This can amount to an implicit language constraint or mismatch without user opt-in, especially for users expecting a fully Chinese-language experience.
Content: No source excerpt is available for this finding.