Back to skill

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 language but no hidden code, credential access, persistence, or destructive behavior.

This skill is reasonable to install if you want generic Gog or Google Workspace workflow guidance. Be aware it may activate too often because its triggers are broad; review any generated commands or workflow changes before applying them, especially for Gmail, Drive, Calendar, or business data.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 manifest description uses broad terms like 'work-productivity,' 'google,' 'workspace,' 'cli,' and generic requests for 'workflow, artifact, checklist, analysis, or implementation support,' which can cause the skill to match many unrelated user prompts. Over-broad activation increases the chance this skill is invoked outside its intended scope, leading to prompt-routing confusion, unsafe delegation, or inappropriate handling of user tasks.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger list contains extremely generic keywords such as 'google,' 'workspace,' 'cli,' 'gmail,' 'calendar,' 'drive,' and 'bug fix,' all of which appear in many ordinary conversations. This makes accidental invocation highly likely and can route sensitive or unrelated tasks into a skill whose instructions and assumptions are not appropriate for the user's actual intent.

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 such as 'google', 'workspace', and 'cli', which can match many unrelated user requests. This can cause the skill to activate outside its intended scope, leading to workflow hijacking, irrelevant guidance, or accidental precedence over more appropriate skills.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger sentence is so broad and natural-language-like that it could match ordinary user requests that were not meant to invoke this skill. In an agent-routing context, that increases the chance of accidental activation, causing the system to apply this workflow in unintended situations and potentially process unrelated Google Workspace or productivity tasks under the wrong assumptions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger examples are generic and broad enough to match many unrelated requests involving productivity, Google, or workflow help. In an agent-routing environment, this can cause over-activation of the skill, leading to incorrect tool selection, prompt collision, or unintended handling of user tasks by a skill not specifically requested.

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, natural-language requests that overlap with ordinary productivity help queries, which can cause the skill to activate when the user did not explicitly intend to invoke it. In an agent ecosystem, unintended invocation can route user tasks through the wrong workflow, producing inappropriate actions, confusing outputs, or over-broad tool use in contexts involving Google Workspace or CLI-related tasks.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The example trigger phrases are written in everyday language and repeat broad problem statements without clearly defining scope, which reinforces permissive matching behavior. When examples are vague, downstream systems or authors may treat a wide range of routine productivity requests as valid activation cases, increasing misrouting and unintended skill use.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The usage condition in the description is vague and mixes broad categories ('work-productivity', 'google', 'cli') with several different task types, without clear boundaries for when the skill should or should not be selected. In agent routing systems, ambiguous scope increases the chance of misrouting sensitive or unrelated requests into this skill, reducing reliability and potentially causing unsafe or incorrect assistance.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The default prompt uses a very broad invocation phrase tied to common productivity terms and an expansive job-to-be-done, which can cause the skill to be selected in contexts the user did not clearly intend. Because implicit invocation is also enabled, this increases the chance of accidental routing, prompt overreach, or unauthorized influence on unrelated conversations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger scope is ambiguous because it mixes broad category keywords with loosely defined example sentences, without strong boundaries on when the skill should or should not activate. In a multi-skill agent environment, ambiguous routing can lead to over-selection of this skill, inappropriate handling of tasks outside its intended scope, and unreliable or unsafe workflow recommendations based on mismatched context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The file list explicitly labels separate English and Chinese instructions and guides, but the README does not explain how the user selects their preferred language or whether language choice is optional. This can create a locale-policy concern if the skill defaults users into a language without clear opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

This is a Chinese README, but the operative usage content, including the skill description and trigger examples, is presented in English only. That can amount to an implicit language preference without user opt-in or explanation.

Content

No source excerpt is available for this finding.