Security audit

Work Productivity Gog Google Workflow Helper

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-style workflow helper with broad routing language but no hidden execution, credential use, persistence, or destructive behavior.

Install only if you want a general workflow/planning helper for Gog-style Google Workspace productivity tasks. Be aware that its trigger terms are broad, so explicit invocation is safer when you want this skill and explicit non-use is sensible for unrelated Google, CLI, or bug-fix requests.

SkillSpector

By NVIDIA

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

Medium

Confidence: 94% confidence
Finding: The trigger sentences are written as natural, generic requests that overlap with ordinary user phrasing, which increases the chance the skill is invoked unintentionally. In an agent environment, accidental invocation can route a conversation into the wrong workflow, causing unintended actions, confusing outputs, or use of connected Google Workspace-related capabilities under the wrong context.

Vague Triggers

High

Confidence: 94% 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 when the user did not explicitly intend to use it. In an agent ecosystem, this creates routing ambiguity and increases the chance that unrelated requests are handled by the wrong workflow, potentially causing unintended actions, irrelevant guidance, or disclosure of context to an unnecessary skill.

Vague Triggers

High

Confidence: 94% confidence
Finding: The skill description is broad enough to activate on generic terms like 'google', 'workspace', and 'cli', which can cause the wrong skill to be selected for unrelated tasks. In an agent environment, overbroad routing increases the chance of prompt/context confusion, unintended tool usage, or unsafe handling of requests outside the skill's intended scope.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The keyword list contains highly ambiguous triggers such as 'google', 'workspace', 'cli', and 'bug fix' that appear in many unrelated user requests. This creates a routing vulnerability where the skill may be invoked unexpectedly, exposing users to irrelevant instructions or causing an agent to apply the wrong workflow in sensitive contexts.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The example trigger phrases are written as everyday requests and do not establish clear activation boundaries, which can train downstream systems or maintainers to match on vague language. While not directly malicious, this increases accidental invocation risk and weakens separation between this skill and other more appropriate skills.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger keywords are very broad and include generic terms like 'google', 'workspace', 'cli', and 'bug fix', which are likely to appear in many unrelated requests. This can cause the skill to activate outside its intended scope, leading to inappropriate routing, irrelevant instructions, or accidental exposure of users to workflow steps that do not match their task.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The skill description says it should be used when a user asks for broad categories like work-productivity, gog, google, workspace, or cli, or needs general workflow/checklist/analysis support. This is ambiguous and overly expansive, making it hard to determine proper activation boundaries and increasing the chance of the skill being selected for unrelated requests.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The skill enables implicit invocation while providing only a very broad, generic description of when it should be used. That creates a prompt-routing weakness where normal conversation about work productivity, Google Workspace, checklists, or implementation help could unintentionally trigger the skill, causing unsolicited influence over the agent's behavior or disclosure of skill behavior in contexts the user did not intend.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The default prompt uses broad, everyday language such as helping with work productivity and practical workflow support, which overlaps heavily with ordinary user requests. In combination with agent routing, this can cause over-broad matching and accidental activation, letting the skill shape responses in situations far outside a tightly bounded use case.

Vague Triggers

High

Confidence: 96% confidence
Finding: The trigger sentence is written as a broad natural-language phrase that overlaps with ordinary user requests, which can cause the skill to activate when the user did not explicitly intend to invoke it. In an agent environment, unintended invocation can redirect workflows, expose unrelated context to the skill, or cause the wrong automation path to run, especially because this skill claims a wide productivity scope across Google Workspace and CLI-style tasks.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The invocation guidance is underspecified and does not define clear activation boundaries, making it easy for generic work-productivity language to match this skill accidentally. Because the skill is positioned as a helper for practical workflows and implementation support, ambiguous routing increases the chance of inappropriate tool selection, confused delegation, and unintended handling of user tasks or data.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.