ClawHub
Back to skill

Security audit

Work Productivity Gog Google Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-style workflow helper with broad auto-invocation metadata but no code, credential access, persistence, or destructive behavior.

Before installing, be aware that the skill may activate for broad productivity or Google-related requests because implicit invocation is enabled and the trigger terms are generic. It appears safe from a security-authority perspective, but users who want predictable routing should narrow the trigger metadata or invoke it explicitly by name.

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 (10)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger phrases are very broad and match common productivity requests such as generic help, practical workflows, or bug-fix assistance. This can cause unintentional skill invocation or over-selection, leading the agent to route ordinary user requests into this skill when the user did not clearly intend it, which is especially risky because the skill spans Google Workspace, CLI, and workflow operations.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill description is broad enough to match many ordinary productivity and Google-related requests, which can cause unintended activation. Over-broad routing increases the chance that this skill intercepts prompts outside its intended scope, leading to incorrect tool behavior, policy bypass via misrouting, or unreliable outputs in multi-skill environments.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The keyword list includes highly generic and high-collision terms such as 'google', 'workspace', 'cli', and 'bug fix', which are likely to appear in many unrelated user requests. In an agent ecosystem, this creates accidental invocation risk and can crowd out more appropriate skills, reducing predictability and creating opportunities for prompt-routing abuse.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger keywords are broad enough to match many ordinary productivity or Google Workspace requests, which can cause this skill to be invoked outside its intended scope. Over-broad auto-invocation increases the chance of prompt collision, unintended handling of unrelated tasks, and user confusion about which workflow or policy is actually controlling the response.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger phrases are broad, repetitive, and loosely scoped, so the skill may activate for generic requests involving productivity, Google, workflows, or bug fixing even when the user did not intend to invoke this specific skill. In an agent environment, overbroad activation can cause the wrong workflow to run, leading to unintended actions, confused delegation, or exposure of user context to an irrelevant skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This Chinese README contains core operational description text in English, which imposes a language choice without stating whether the skill supports user-preferred language output. The file does not document any opt-in or justified locale constraint, so it may conflict with language-choice expectations.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The example triggers are phrased as generic help requests and do not define meaningful activation boundaries. Ambiguous examples train the router or authoring pattern toward matching loosely similar requests, increasing false activations and reducing confidence that the selected skill is the right one.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The description includes a catch-all condition covering users who need 'practical workflow, artifact, checklist, analysis, or implementation support' for a very broad requirement area. This ambiguity makes the router likely to select the skill for loosely related requests, creating unintended activation and reducing predictability of agent behavior.

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 broad, common terms such as work-productivity, google, workspace, cli, workflow, checklist, analysis, and implementation support, which can cause the skill to be invoked in many unrelated conversations without strong scoping. Because implicit invocation is enabled, this increases the chance of unintended routing, prompt-surface expansion, and accidental application of the skill in contexts where its instructions or assumptions do not fit.

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, generic, and closely resemble ordinary user requests, which can cause the skill to activate in situations outside its intended scope. In an agent-routing context, this can lead to misclassification, unnecessary invocation of this skill, and reduced trust or safety if the wrong workflow is applied to unrelated tasks.

Content

No source excerpt is available for this finding.