Unit Test Coverage Helper

• Outcome: Pass
• Latest audit: Jul 24, 2026 · 5:15 PM UTC
• Version: 0.1.0

Overview

This is a low-risk testing workflow skill with broad auto-routing wording but no executable code, hidden behavior, persistence, or credential access.

Installers should know this skill may be invoked automatically for general testing or quality-related requests. Use explicit invocation when possible if you want predictable routing, and review any proposed code or test changes before applying them.

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 (11)

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The trigger sentence is broad enough to match ordinary help-seeking language rather than a narrowly scoped invocation. In agent environments that auto-select skills from user phrasing, this can cause unintended activation and route unrelated requests into this skill, increasing the chance of incorrect behavior or prompt-scope confusion.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The invocation guidance does not define clear trigger boundaries, so common phrases may activate the skill even when the user did not intend to use it. This ambiguity is more dangerous in a broadly applicable software/testing context because many unrelated developer requests could partially match these patterns.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The trigger phrases are broad enough to match ordinary requests about unit tests, coverage, testing, or workflows, which can cause the skill to activate in situations the user did not explicitly intend. In an agentic system, over-broad activation expands the skill's influence surface and can lead to unintended instruction injection, priority inversion, or misrouting of benign requests into a more powerful workflow.

Vague Triggers

High

• Confidence: 93% confidence
• Finding: The skill description is broad enough to match many ordinary software requests, which can cause the skill to activate outside its intended scope. Over-broad routing increases the chance that unrelated user requests are handled by this skill, potentially leading to incorrect guidance, unintended prompt injection surface expansion, or interference with more appropriate specialized skills.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The example trigger phrases use generic everyday wording that could match a wide range of normal requests without sufficient specificity. This makes accidental invocation more likely and can degrade routing integrity by selecting this skill when a more precise skill or default handling would be safer and more appropriate.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger keywords and example phrases are broad enough to match many ordinary requests about testing, regression, or quality, which can cause the skill to activate outside its intended scope. Over-broad activation is dangerous because it can override more appropriate skills or inject irrelevant workflows into unrelated conversations, reducing reliability and potentially steering users toward unintended actions.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The skill description says to use the skill whenever users ask for broad categories such as software-and-data, unit tests, test coverage, testing, or regression, but it does not define exclusion criteria or prioritization. In a multi-skill environment, this ambiguity increases the chance of accidental invocation and scope confusion, which can misroute user requests and degrade safety controls based on proper skill selection.

Vague Triggers

Medium

• Confidence: 84% confidence
• Finding: The default prompt is written in broad, natural language and includes common terms like unit tests, test coverage, and testing. In combination with an auto-routing system, this can cause the skill to activate for loosely related requests, increasing the chance of unintended invocation and context overreach rather than direct code-execution risk.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: Implicit invocation is enabled without visible constraints on when the skill should be selected. That makes accidental or overly broad routing more likely, which can expose user context to the skill or cause inappropriate assistance in conversations that only tangentially mention testing-related concepts.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The trigger sentence "Help me Teams need repeatable help adding useful unit tests and raising test coverage for existing codebases" is overly broad and begins with common conversational language, making accidental activation more likely. In an agent-routing system, broad triggers can cause this skill to hijack unrelated requests about testing or general software help, leading to misrouting, inappropriate context application, or unintended execution of workflow instructions.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The invocation examples do not meaningfully limit activation conditions and effectively encourage matching on generic requests for help or practical workflows. This increases the chance that the skill is selected in contexts where it is not the best fit, which can degrade agent reliability and, in multi-skill systems, create a prompt-routing vulnerability where a low-risk documentation skill overrides more appropriate specialized handling.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.