Error Message Improver

• Outcome: Pass
• Latest audit: Jul 29, 2026 · 4:51 AM UTC
• Version: 0.20260729.110214

Overview

This is a documentation-style skill for improving error messages, with no code execution, credential access, persistence, or hidden data handling found.

Installers should be aware that this skill may be selected for general debugging or support prompts because its triggers are broad. It does not appear to run code or access private data, but tighter trigger wording would make it easier to predict when it activates.

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 (9)

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The trigger phrases are written as broad, natural-language requests such as 'Help me...' and 'I need a practical workflow...', which can match many ordinary user prompts and cause the skill to activate unintentionally. In an agent environment, over-broad activation can route unrelated user input into this skill, leading to prompt hijacking of workflow selection, confusion, or inappropriate handling of requests.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The manifest description uses very broad phrases such as helping with work-productivity, debugging, support, workflows, artifacts, analysis, and implementation support. In skill-selection systems, this can cause the skill to activate for many unrelated user requests, increasing prompt-scope hijacking risk and allowing this skill to override more appropriate, narrower skills.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger keywords include generic terms like debugging, support, troubleshooting, and user feedback, which are common across many unrelated tasks. Overbroad triggers make accidental invocation more likely, letting the skill insert instructions and behavior in contexts far outside error-message improvement.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The example trigger sentences are phrased as broad everyday requests for help and practical workflows, without clear boundaries on when this skill should or should not activate. This ambiguity can cause unreliable routing and unintentional selection in routine assistance scenarios.

Vague Triggers

Medium

• Confidence: 87% confidence
• Finding: The trigger conditions are broad and overlap with common support and productivity requests, which can cause the skill to activate in situations beyond its intended scope. Overbroad activation is risky because it may route unrelated user requests into a specialized workflow, leading to poor task handling, hidden prompt influence, or unintended instruction precedence across ordinary conversations.

Natural-Language Policy Violations

Medium

• Confidence: 80% confidence
• Finding: The skill content is entirely in Chinese and does not indicate language selection behavior or a justified locale restriction. This can cause misuse or unsafe delegation when users operate in another language, increasing the chance of misunderstanding instructions, verification criteria, or generated support content in ways that reduce reliability and user control.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The skill enables implicit invocation without any visible trigger scoping or constraints, which increases the chance that it will be auto-selected for loosely related user requests. Because this skill is framed around broad support and productivity tasks, unintended invocation could cause overreach, prompt-surface expansion, or interference with user intent across many normal conversations.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The default prompt uses very broad, everyday phrasing such as work-productivity, debugging, user feedback, support, workflow, artifact, checklist, analysis, and implementation support. In combination with implicit invocation, this broad language can match a wide range of unrelated requests, causing the skill to activate when not appropriate and potentially influence outputs outside its intended domain.

Vague Triggers

High

• Confidence: 94% confidence
• Finding: The trigger sentence is so broad and awkwardly templated that it can match ordinary user requests about help, workflows, or error handling, causing the skill to activate outside its intended scope. Over-broad activation is dangerous because it can hijack routing, suppress more appropriate skills, and create prompt-surface expansion where unrelated conversations are pulled into this skill unexpectedly.

VirusTotal

61/61 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.