Work Productivity Humanizer Remove Workflow Helper

• Outcome: Pass
• Latest audit: Jul 24, 2026 · 5:23 PM UTC
• Version: 0.1.0

Overview

This is a documentation-only workflow helper with broad activation wording, but it does not add hidden execution, credential access, persistence, or destructive behavior.

Before installing, be aware that this skill may activate for broad terms like writing, text, editing, or bug fix. It appears safe as a documentation workflow helper, but narrowing invocation wording would reduce accidental activation.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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 (13)

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The trigger sentence is broad, generic, and closely resembles ordinary user requests, which increases the chance the skill will be invoked unintentionally for unrelated conversations. In an agent environment, over-broad activation can route benign tasks into this skill unexpectedly, causing workflow hijacking, irrelevant instructions, or unsafe automation drift.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The activation guidance does not clearly define boundaries, exclusions, or prerequisite conditions for using the skill, so agents may invoke it in contexts far outside its intended purpose. Because the README mixes broad productivity language with vague workflow claims, it increases ambiguity and raises the risk of accidental or excessive delegation.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger phrases are extremely generic and overlap with normal user requests such as asking for help, workflows, writing, editing, or bug fixes. This can cause unintended skill activation, routing user tasks into this skill without clear user intent, which increases the risk of mis-execution, confusion, and privilege misuse in agent environments where skills may perform automated actions.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The skill description is scoped to a very broad set of common requests and includes generic activation language like practical workflow, artifact, checklist, analysis, or implementation support. In an agent environment, this can cause unintended routing or over-invocation on ordinary user requests, expanding the skill’s influence beyond its intended domain and potentially bypassing more appropriate, safer skills.

Vague Triggers

High

• Confidence: 99% confidence
• Finding: The keyword list contains highly generic terms such as remove, signs, generated, writing, text, editing, reviewing, and bug fix, which are common across many unrelated tasks. These broad triggers make accidental activation likely and can let the skill intercept benign or unrelated conversations, creating unsafe overreach and reducing routing integrity.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The example trigger phrases are written as broad, natural everyday requests without meaningful scope constraints, which reinforces overmatching behavior in systems that use examples for activation. This increases the chance that the skill will be selected for loosely related requests, causing confusion, policy drift, or unintended execution paths.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger list includes very broad everyday terms such as "writing", "text", "editing", "reviewing", and "bug fix", which can cause the skill to activate for many unrelated requests. Over-broad activation increases the chance that the wrong skill handles user input, producing unintended transformations or workflow guidance outside the user's intent.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The description says the skill should be used whenever the user mentions broad categories like work-productivity, humanizer, remove, signs, or generated, or when they need practical workflow support. This boundary is too vague, making routing ambiguous and increasing the risk of accidental invocation for unrelated requests.

Natural-Language Policy Violations

Medium

• Confidence: 78% confidence
• Finding: The skill content is presented entirely in Chinese without stating language selection behavior or whether users may interact in other locales. This can lead to incorrect language handling, user confusion, or policy noncompliance when the runtime expects locale-aware behavior.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The default prompt includes a very broad invocation phrase tied to common terms like 'work-productivity' and generic help requests, which can cause the skill to activate in ordinary conversations where the user did not intend to call it. This increases the risk of prompt hijacking of normal user flows, unexpected behavior, and accidental exposure of the skill's instructions or side effects.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: Enabling implicit invocation without clear constraints allows the platform to auto-select this skill based on vague similarity, even when the user's request only loosely matches the description. In combination with the broad productivity-oriented wording of this skill, that can lead to unintended activation across many benign conversations, increasing the chance of misexecution, confusion, or abuse through crafted prompts.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The trigger sentences are broad, generic, and match ordinary user requests like asking for practical workflows or help with bugs/hardening. This can cause the skill to activate in situations far outside its intended scope, leading to unintended interception of user tasks, misrouting, and overbroad application of the skill's guidance.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The activation guidance does not define firm boundaries for when the skill should or should not be used, and the listed keywords are highly ambiguous. In agent systems, vague routing criteria can produce systematic over-triggering, causing incorrect tool selection, degraded reliability, and possibly bypass of more appropriate specialized skills.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.