Security audit

Work Productivity Humanizer Remove Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-style workflow skill with overbroad activation wording but no executable code, credential handling, persistence, or hidden data access.

Install only if you want a general workflow/checklist helper for Humanizer-style productivity tasks. Be aware that its broad trigger wording may cause it to activate for ordinary writing or editing requests unless your platform lets you require explicit invocation.

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: 97% confidence
Finding: The trigger keywords are so broad that this skill can be invoked for ordinary writing, editing, or review tasks far outside the intended scope. In an agent system, that creates routing ambiguity and can cause the model to apply a 'humanizer/remove signs generated' workflow to benign content, increasing the chance of deceptive rewriting, policy bypass by indirection, or unintended takeover from more appropriate specialized skills.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentences and keywords are broad, generic, and partially malformed, which can cause the skill to activate for unrelated user requests. In an agent environment, unintended activation can route tasks into the wrong workflow, causing misleading outputs, context confusion, or inappropriate handling of sensitive requests.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The invocation guidance lists generic keywords and trigger patterns without defining when the skill must not be used, which makes activation criteria ambiguous. This is dangerous because broad matching can cause unintended skill execution, especially in shared agent environments where many user requests contain common terms like help, workflow, writing, editing, or bug fix.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger examples are phrased broadly enough that normal user requests about help, workflows, or fixing bugs could accidentally activate this skill outside its intended scope. In an agent routing system, ambiguous activation increases the chance of misrouting, causing the wrong instructions or transformations to be applied to unrelated user tasks.
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 partially templated around common productivity and writing requests, which can cause the skill to activate in situations the user did not clearly intend. In an agent ecosystem, overbroad activation increases the chance of misrouting tasks, applying the wrong workflow, or unexpectedly transforming user content, especially because the skill is positioned for broad "work-productivity" and "humanizer" use cases.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The invocation rule uses a vague 'Use when a user asks...' formulation with minimal boundaries, which makes the skill eligible for many loosely related requests. That weak scoping can lead to inappropriate auto-selection, conflicting behavior with safer domain-specific skills, and easier misuse for requests framed to disguise intent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The example triggers are generic and repetitive, and they do not teach the router or user how to distinguish valid use from adjacent or unsafe use. Poor trigger examples broaden activation in practice, making accidental invocation and misuse more likely, especially in systems that rely on natural-language matching.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill description says it should be used when users mention broad keywords or need general workflow, checklist, analysis, or implementation help, but it does not clearly define boundaries for this specific skill. This ambiguity makes the router more likely to invoke the skill for loosely related requests, which can degrade reliability and create unsafe or inappropriate handling in edge cases.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger list includes very common words such as “remove”, “text”, “editing”, “reviewing”, and “bug fix”, which substantially increases the chance of accidental activation in unrelated conversations. Over-broad activation can cause the wrong skill to take control, leading to misrouting, confusing outputs, and bypass of more appropriate safety or domain-specific handling.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The default prompt is broadly worded and includes common phrases like "help me" and generic productivity language, which can cause the skill to be selected in situations far outside its intended scope. When combined with an agent routing system, this increases the chance of unintended invocation, context hijacking, or the model applying the skill to unrelated user requests.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Enabling implicit invocation without clear trigger boundaries allows the platform to auto-select this skill based on weak semantic matches. Because the skill description and prompt are already broad, this setting materially increases the risk of accidental activation, inappropriate task handling, and interference with safer or more relevant skills.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: The file is a zh-CN README, but key instructional content is presented in English, which can impose a language choice on users without opt-in. This may violate language or locale expectations because the document does not explain the mixed-language behavior or offer an alternative within that section.
Content: No source excerpt is available for this finding.