Work Productivity Humanizer Remove Workflow Helper

• Outcome: Pass
• Latest audit: Sep 6, 2026 · 4:20 AM UTC
• Version: 0.20260906.40422

Overview

This is a documentation-only workflow helper with overly broad activation wording but no hidden code, persistence, credential use, or destructive behavior.

Before installing, be aware that this skill may be invoked too easily for generic writing, editing, or bug-fix requests because of broad trigger terms and implicit invocation. It does not appear to install code or access sensitive data, but users who want precise routing should narrow the triggers or disable implicit invocation.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (10)

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The trigger sentence is phrased as a broad, ordinary request that could match many unrelated user prompts and cause the skill to activate unintentionally. In an agent environment, over-broad invocation can route tasks to the wrong workflow, leading to unsafe or irrelevant actions, confusion, or policy bypass through accidental skill selection.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The usage section defines activation through ambiguous natural-language examples without clear boundaries, making it easy for the orchestrator or user to invoke the skill for loosely related productivity or writing requests. Because this skill appears to target a broad work-productivity context, ambiguous triggers increase the chance of unintended execution across many benign conversations.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The trigger phrases are generic and semantically broad, including common help-seeking language such as asking for a practical workflow or help with bugs/hardening. In an agent ecosystem, this can cause unintended auto-invocation during ordinary conversation, routing user requests into this skill without clear intent and potentially producing irrelevant or unsafe workflow actions.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The skill description and usage guidance are broad enough to match many ordinary requests, which can cause the skill to activate outside its intended scope. Over-broad activation increases the chance of unintended delegation, irrelevant instruction injection into workflows, and user confusion about why a specialized skill was invoked.

Vague Triggers

High

• Confidence: 98% confidence
• Finding: The keyword list includes generic terms such as 'remove', 'signs', 'generated', 'writing', 'text', and 'reviewing' without contextual constraints. These common words are likely to appear in unrelated conversations, making accidental triggering highly probable and potentially routing benign requests through unintended instructions.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The example trigger phrases are written in broad natural language and do not define clear activation boundaries, which normalizes ambiguous invocation patterns. This can lead maintainers or orchestrators to implement permissive matching behavior that over-invokes the skill in unrelated contexts.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger section includes very broad, common keywords such as "remove", "generated", "text", "editing", and "bug fix", plus generic example invocations. This can cause the skill to activate in many unrelated contexts, leading to unintended instruction injection into user workflows and increasing the chance that an irrelevant or unsafe skill is selected automatically.

Natural-Language Policy Violations

Medium

• Confidence: 82% confidence
• Finding: The skill is authored entirely as a Chinese-language variant without stating how language should be selected or whether responses should adapt to the user's language. This can cause misalignment, user confusion, or incorrect task execution when the skill is invoked by users operating in another language, especially if the system routes based on metadata rather than user preference.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The default prompt contains a very broad natural-language trigger phrase and the skill also allows implicit invocation, which increases the chance the agent will auto-select this skill during ordinary conversation unrelated to the user's actual intent. This can cause unintended prompt injection into sessions, confusing behavior, or execution of the skill in contexts where it was not explicitly requested.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The trigger sentences are generic enough to match ordinary user requests and even include a direct invocation pattern, which can cause the skill to activate outside its intended scope. In an agent environment, over-broad activation can route unrelated conversations into this skill, creating prompt hijacking opportunities, incorrect handling, and unsafe interference with normal task selection.

Static analysis

No suspicious patterns detected.