Work Productivity Gog Google Workflow Helper

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 5:33 AM UTC
• Version: 0.20260910.52416

Overview

This is a documentation-only workflow helper with overly broad activation wording, but it does not contain code, credential handling, persistence, exfiltration, or destructive behavior.

Install only if you want a broad workflow-planning helper. Be aware it may activate on ordinary Google Workspace, CLI, Gmail, Drive, Calendar, Contacts, or bug-fix prompts unless your agent requires explicit skill selection; prefer explicit invocation for sensitive work.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (13)

Vague Triggers

High

• Confidence: 98% confidence
• Finding: The skill description is broad enough to match many ordinary productivity, Google, CLI, workflow, and analysis requests, which can cause the skill to activate outside its intended scope. Over-broad activation increases the chance of prompt-surface hijacking, unintended routing, and the application of this skill's assumptions to unrelated tasks, degrading safety and correctness.

Vague Triggers

High

• Confidence: 99% confidence
• Finding: The keyword list contains highly collision-prone terms such as 'google', 'workspace', 'cli', 'gmail', 'calendar', 'drive', and 'bug fix', all of which commonly appear in benign requests unrelated to this specific skill. This makes accidental invocation likely and can let the skill intercept unrelated user requests, creating misrouting and expanding the attack surface for prompt injection or policy bypass through inappropriate tool selection.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger list is very broad and includes generic terms like "google", "workspace", "cli", and "bug fix", which are common in ordinary conversations and likely to cause unintended activation. Over-broad activation can route unrelated user requests into this skill, creating prompt-scope confusion and increasing the chance that the assistant applies irrelevant workflow instructions or exposes users to lower-quality or unsafe task handling.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger sentence uses a very broad everyday help phrase tied to a large requirement blurb, which can cause the skill to activate for loosely related requests. In an agent environment, overbroad activation increases the chance of unintended tool or workflow invocation, producing irrelevant outputs or routing user data into the wrong process.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The README provides trigger guidance without clear boundaries on when the skill should and should not activate, while also covering a broad set of domains such as Google Workspace, CLI, Gmail, Calendar, Drive, and Contacts. This ambiguity increases the chance of accidental invocation and scope creep, which is more dangerous in a productivity/integration skill because it may influence actions across multiple connected services.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The trigger sentence is phrased as a very common help request and embeds broad natural-language wording that could match ordinary user prompts unintentionally. In an agent ecosystem, overly generic activation phrases can cause the skill to invoke when the user did not intend it, potentially steering workflows, exposing connected-tool context, or interfering with other more appropriate skills.

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: The trigger phrases are broad and generic enough to match many unrelated requests involving work productivity, Google Workspace, or bug fixing. In an agent ecosystem, this can cause accidental skill activation and context capture, leading the wrong workflow to run on user data or displacing a more appropriate skill.

Natural-Language Policy Violations

Medium

• Confidence: 91% confidence
• Finding: The file explicitly labels this README and related documentation as Chinese and English variants, but this specific file presents the user-facing content entirely in Simplified Chinese without stating that language selection is optional. Because language/locale policy violations apply to all file types, presenting the skill in a fixed locale without user opt-in is a natural-language policy concern.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The example trigger sentences are so general that they do not establish clear activation boundaries, reinforcing the broad routing behavior defined elsewhere. Poorly specified examples teach downstream systems and authors that minimal mention of productivity hardening is sufficient, which increases false activation and unreliable behavior.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The invocation description says to use the skill for broad categories like work-productivity, gog, google, workspace, and CLI support, but it does not clearly define boundaries for when the skill should or should not activate. This ambiguity can lead to accidental invocation on loosely related requests, causing misrouting and reducing reliability of skill selection.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The skill enables implicit invocation, but its trigger description is broad and generic rather than narrowly scoped to specific user intents. This can cause the agent to auto-select the skill in situations the user did not clearly request, increasing the chance of unintended actions, overbroad tool use, or unsafe handling of workspace-related tasks.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The phrase 'I need a practical workflow for ...' is a generic request pattern that could match many unrelated user prompts. This ambiguity makes unsafe or incorrect activation more likely, especially because the skill covers broad work-productivity and Google-adjacent tasks that may touch sensitive enterprise workflows.

Natural-Language Policy Violations

Low

• Confidence: 84% confidence
• Finding: The evidence list includes Chinese-language text ('ONES 研发管理') while the rest of the document is in English, but the skill does not state that multilingual or Chinese-language content is intentional or user-selected. This can conflict with a language/locale policy requiring explicit user opt-in or documented justification.

Static analysis

No suspicious patterns detected.