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 code, but its activation wording is too broad.

Install only if you want a broad planning/checklist helper for Gog-style Google Workspace workflow work. Because implicit invocation is enabled with generic keywords, users or maintainers should prefer explicit invocation or narrow the triggers to avoid this skill appearing during unrelated Google, CLI, or productivity 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 (12)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The manifest description uses broad terms like work-productivity, google, workspace, cli, workflow, artifact, checklist, and analysis without strong boundary conditions, so the skill may activate for many ordinary requests outside its intended niche. Overbroad activation can cause inappropriate routing, unexpected execution of the skill, and reduced user control over which instructions influence the agent.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger list includes very high-collision keywords such as google, workspace, cli, gmail, calendar, drive, contacts, and bug fix, all of which commonly appear in unrelated conversations. This makes accidental invocation likely and increases the chance that the skill injects instructions or workflow assumptions into contexts where they do not belong.
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', and 'cli', which can match many unrelated user requests. This can cause the skill to activate outside its intended scope, increasing the chance of incorrect delegation, prompt collisions, or the skill being invoked in contexts involving sensitive productivity data without a clear need.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger sentence is broad enough to match ordinary user phrasing and can cause the skill to activate outside its intended scope. In an agent environment, unintended invocation can route unrelated requests into this workflow, creating prompt hijacking opportunities, incorrect tool selection, or accidental exposure of sensitive workspace-related context.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The request pattern is vague and lacks scope constraints, so the skill may claim relevance for loosely related productivity or workflow requests. That increases the chance of misrouting tasks, over-collection of user context, and unsafe execution paths if the agent assumes this skill is appropriate without strong intent verification.
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 can activate on generic requests involving common terms like 'google', 'workspace', 'cli', or 'bug fix', increasing the chance the skill is invoked outside its intended scope. In an agent ecosystem, overbroad activation can route unrelated user tasks into this skill, causing incorrect automation, unsafe assumptions, or unintended handling of sensitive productivity workflows.
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, generic, and include common terms like 'google', 'workspace', and 'bug fix', which can cause this skill to activate for routine user requests outside its intended scope. In an agent environment, over-broad invocation can route unrelated tasks into a workflow with different assumptions, increasing the chance of incorrect actions, unintended data handling, or user confusion.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The example trigger sentences are broad and self-referential, reinforcing activation from vague requests rather than demonstrating clear eligibility rules. Because they model ambiguous invocation behavior, they can train routing systems or authors toward over-activation and make unintended skill selection more likely.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The activation condition in the description is vague, saying the skill should be used when users ask for broad categories like work-productivity, google, workspace, or practical support, without clearly defining inclusion and exclusion criteria. Ambiguous routing guidance can lead to over-activation, unintended handling of unrelated tasks, and reduced safety because the skill may be selected in situations it was not designed to handle.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt is highly generic and includes broad terms like work-productivity, google, workflow, and practical help, which can match many normal user requests unrelated to this specific skill. In combination with implicit invocation, this creates a prompt-squatting risk where the skill may be auto-selected unexpectedly, causing unintended instruction injection or workflow interference.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: Enabling implicit invocation without strict trigger constraints allows the platform to auto-activate this skill based on ambiguous user language. Because the skill is positioned around common productivity and Google Workspace workflows, many benign prompts could unintentionally invoke it, increasing the chance of unauthorized context influence or execution of irrelevant workflow guidance.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This file is presented as a Chinese README, but substantial user-facing content is in English, including the main requirement description. That can effectively impose a language choice on users of the zh-CN variant without opt-in or an explicit bilingual note.
Content: No source excerpt is available for this finding.