Work Productivity Humanizer Remove Workflow Helper

• Outcome: Pass
• Latest audit: Jul 29, 2026 · 5:47 AM UTC
• Version: 0.20260729.110214

Overview

This is a low-capability workflow/documentation skill with overly broad triggers, but no hidden execution, persistence, credential use, or destructive behavior was found.

Install only if you want a general workflow helper for Humanizer-style skill/work-productivity tasks. Be aware that its broad keywords and implicit invocation may make it activate on ordinary writing, editing, or bug-fix requests where a more specific skill would be better.

SkillSpector

By NVIDIA

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: 93% confidence
• Finding: The trigger phrases are generic and overlap with ordinary requests such as asking for help, needing a workflow, or handling bug fixing and hardening. In an agent ecosystem, this can cause the skill to activate outside its intended scope, leading users or other skills into an unexpected workflow and increasing the chance of prompt hijacking, misrouting, or accidental execution of inappropriate instructions.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The trigger phrases are extremely broad and map to common, everyday requests such as asking for help or needing a practical workflow. This can cause the skill to activate outside its intended scope, increasing the chance of misrouting user requests, unintended skill invocation, and unsafe automation in contexts the skill was not designed to handle.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The trigger keywords are extremely broad and include common terms like 'remove', 'text', 'writing', and 'bug fix', which can cause the skill to activate for many unrelated user requests. Overbroad activation increases the chance that the wrong skill handles a task, leading to confusing behavior, unintended workflow execution, and possible bypass of more appropriate scoped skills or safeguards.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The description acts as a catch-all by saying to use the skill whenever a user 'needs a practical workflow, artifact, checklist, analysis, or implementation support,' which covers a very large share of normal agent interactions. This ambiguity makes routing unpredictable and can cause the skill to intercept requests outside its intended domain, reducing reliability and increasing the risk of inappropriate or unsafe task handling.

Vague Triggers

Low

• Confidence: 88% confidence
• Finding: The example triggers are themselves vague and mostly restate broad demand language rather than concrete user intents, reinforcing loose matching behavior. This makes it more likely that the skill will be selected on ambiguous phrasing instead of precise task fit, contributing to misrouting and degraded control over agent behavior.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The trigger keyword list is overly broad and includes generic terms such as 'writing', 'text', 'editing', 'reviewing', and 'bug fix'. This can cause the skill to activate in many unrelated contexts, increasing the chance that it overrides a more appropriate skill or injects irrelevant workflow guidance into normal conversations.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The skill description defines activation conditions in a broad and ambiguous way, including users who need any 'practical workflow, artifact, checklist, analysis, or implementation support' for loosely related terms. This weak boundary makes accidental invocation likely and can lead to capability overreach, confusing routing, or unintended influence on tasks outside the intended scope.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The default prompt includes a very broad natural-language trigger phrase covering common terms like 'work-productivity' and generic help requests, while implicit invocation is enabled. This can cause the skill to activate unexpectedly during ordinary user conversations, leading to unintended routing, prompt injection surface expansion, or execution of the wrong workflow without clear user intent.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The trigger examples include broad natural-language phrases such as 'Help me' and 'I need a practical workflow' that are common in ordinary user requests and not specific to this skill's narrow purpose. In an agent-routing system, this can cause accidental invocation on unrelated prompts, creating prompt-scope confusion and increasing the chance that the wrong skill handles sensitive or high-impact tasks.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The invocation guidance is ambiguous and malformed, mixing requirement text directly into trigger sentences without clearly defining when the skill should or should not activate. This weak scoping can lead to overbroad matching, unintended skill execution, and misrouting of user requests, which is more dangerous in agentic environments where downstream actions may be taken automatically.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.