Unit Test Coverage Helper

• Outcome: Pass
• Latest audit: Jul 29, 2026 · 5:51 AM UTC
• Version: 0.20260729.110214

Overview

This skill is a straightforward unit-test coverage helper with no hidden execution, persistence, credential use, or destructive behavior.

This skill is reasonable to install for unit-test and coverage work. Users should be aware it may activate on broad software-testing language, so explicit invocation or narrower routing would reduce accidental use in unrelated development tasks.

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 broad natural-language prompts that can match ordinary user requests such as asking for help or a practical workflow. In an agent-routing system, this can cause unintended invocation of the skill, leading to prompt/skill hijacking of unrelated conversations and inappropriate access to user context or workflow control. The unit-testing context makes this less severe than a destructive skill, but the overlap still creates a real routing and scope-control weakness.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The trigger phrases are broad enough to match many ordinary software-help requests, which can cause this skill to activate outside its intended scope. In an agent system, overbroad routing can expose users to unintended workflows, create prompt-injection surface area, and let the skill influence tasks it was not specifically selected for.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The skill description uses broad trigger terms like 'software-and-data', 'testing', and 'regression' that are common across many unrelated developer tasks. This can cause the skill to activate outside its intended scope, increasing the chance that an agent applies testing-specific guidance in the wrong context or overrides a more appropriate skill.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The example trigger phrases are written in generic natural language ('Help me...', 'I need a practical workflow...') with little disambiguation beyond repeated requirement text. Overly generic examples can bias routing systems toward matching ordinary requests, leading to accidental invocation and reduced trust in skill boundaries.

Vague Triggers

Medium

• Confidence: 88% confidence
• Finding: The trigger keywords include broad generic terms like "testing", "regression", and "quality", which can cause the skill to activate in many unrelated conversations. Overbroad activation increases the chance the agent injects irrelevant guidance, overrides more appropriate skills, or exposes internal workflow behavior in contexts where the user did not request test-coverage help.

Vague Triggers

Medium

• Confidence: 85% confidence
• Finding: The skill description defines activation conditions with a wide and blurry scope, covering broad categories like software-and-data, testing, and regression, plus requests for workflows, artifacts, analysis, or implementation support. This makes accidental invocation likely across many software tasks, which can misroute user requests and create unsafe or low-quality agent behavior through context confusion.

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The default prompt uses very broad natural-language triggers such as software-and-data, unit tests, test coverage, testing, regression, workflow, artifact, checklist, analysis, and implementation support. With implicit invocation enabled, this can cause the skill to activate for loosely related requests outside its intended scope, increasing the chance of unintended delegation, context leakage, or user confusion about why the skill was invoked. The content is not overtly malicious, but the trigger boundaries are insufficiently precise for safe routing.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The trigger sentence begins with a very broad everyday phrase ('Help me'), which can cause the skill to activate in contexts far beyond its intended unit-testing scope. In agent systems, overly generic activation language can lead to unintended routing, prompt collisions, or invocation when a user did not intend to use this skill, increasing the chance of inappropriate actions or disclosure of unrelated context.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The invocation guidance and trigger list do not clearly define the boundaries for when this skill should and should not activate. Because the skill is framed around common software-assistance terms and practical workflow requests, ambiguous scope can cause accidental invocation for unrelated development tasks, resulting in misrouting and unsafe overreach by the agent.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.