Security audit

Work Productivity Gog Google Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with no executable payload or persistence, though its automatic activation terms are broader than ideal.

Install this only if you want a broad Google/Gog productivity workflow helper. Because implicit invocation is enabled with generic terms, users or maintainers should prefer explicit invocation or narrower trigger phrases to avoid accidental use on unrelated Google, CLI, or bug-fix requests.

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 (13)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill description includes very broad activation terms such as 'google', 'workspace', 'cli', 'analysis', and 'implementation support', which overlap with a large volume of ordinary user requests. This can cause the skill to activate outside its intended scope, leading to incorrect tool routing, unintended instruction injection into unrelated tasks, or opportunistic capture of benign workflows by this skill.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The keyword list contains generic triggers including 'google', 'workspace', 'cli', 'gmail', 'calendar', 'drive', and 'bug fix', all of which are common across many unrelated tasks. In an agent ecosystem, such broad triggers materially increase accidental invocation and can let this skill supersede more appropriate or safer skills for unrelated requests.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keywords are overly broad and include common terms like 'google', 'workspace', 'cli', and 'bug fix', which can cause the skill to activate for unrelated requests. This increases the chance of unintended routing, causing users to receive irrelevant guidance or the wrong workflow in contexts where precision matters.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger sentence begins with a very broad everyday phrase ('Help me'), which can cause the skill to activate on many unrelated user requests. In an agent environment, over-broad activation increases the chance of unintended routing, prompt injection exposure, or accidental use of this skill in contexts where it should not run.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are broad, generic, and include common productivity terms that could cause the skill to be invoked in situations the user did not clearly intend. In an agent setting, unintended invocation can route user data or tasks into the wrong workflow, causing confusion, incorrect actions, or accidental processing of Google Workspace-related requests under inappropriate assumptions.
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 enough to match ordinary user requests about productivity, Google Workspace, or bug fixing, which can cause the skill to activate outside the author's intended scope. In an agent ecosystem, this can lead to unintended routing, prompt overshadowing, or the skill influencing tasks it was not explicitly selected for, reducing reliability and potentially exposing downstream workflows to inappropriate instructions.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The example trigger phrases use vague everyday wording like 'Help me' and 'I need a practical workflow', which are too general to safely signal this specific skill. Examples often shape runtime matching behavior and author/user expectations, so overly broad phrasing increases the chance of mistaken activation on routine productivity requests.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 85% confidence
Finding: 该技能文件整体以中文编写，且未说明这是可选语言、未提供多语言选项，也未声明该技能仅面向特定中文环境用户。根据语言/locale 政策，若技能隐含强制特定语言而没有用户选择或明确正当理由，属于自然语言策略风险。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The description says to use the skill when a user asks for broad categories like work-productivity, google, workspace, or practical support, but it does not define clear boundaries for applicability. This ambiguity can lead to over-triggering and misuse, especially in multi-skill environments where routing decisions depend on precise scope.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The default prompt trigger phrase is broad and overlaps with common user language about work productivity, Google Workspace, workflows, checklists, and implementation help. Because implicit invocation is enabled, ordinary conversation can unintentionally activate this skill, causing prompt/context injection into unrelated sessions and making the skill easier to trigger without clear user intent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: Although the sentence adds some context, it still remains ambiguous and is not anchored to a precise task, product boundary, or action. This can misclassify user intent and cause the skill to capture requests outside its safe scope, especially because the skill is framed broadly around workflows, analysis, and implementation support.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: SQP-3 applies to all file types, including markdown. Listing fixed language variants for the skill and guide without stating that users may choose their preferred language can be read as a language constraint, and the file does not document any opt-in or selection behavior.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: This file is presented as a Chinese README, but key user-facing descriptive content is written in English, which can impose a language preference without user opt-in. No explanation is given for why the mixed-language presentation is required or how users can choose their preferred language.
Content: No source excerpt is available for this finding.