Unit Test Coverage Helper

• Outcome: Pass
• Latest audit: Jul 24, 2026 · 5:08 PM UTC
• Version: 0.1.0

Overview

This is a documentation-only helper for unit-test coverage work, with broad auto-invocation language but no hidden execution, persistence, credential use, or exfiltration behavior.

Before installing, be aware that the skill may be selected for fairly general testing or quality requests. It is otherwise a plain workflow helper; users who want tighter behavior should narrow activation to explicit unit-test coverage or regression-test requests.

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: 87% confidence
• Finding: The trigger sentences are generic and templated enough that the skill could activate for broad testing-related requests without clear user intent to invoke this specific workflow. In an agent ecosystem, overly broad activation can cause misrouting, unnecessary context capture, or execution of the wrong skill, which is a real security and safety issue even though the content here is not overtly malicious.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The trigger phrases are broad enough to match ordinary testing-related requests, which can cause the skill to activate outside narrowly intended scenarios. In an agent system, over-broad routing can steer users into a canned workflow, increase prompt-surface for indirect instruction influence, and crowd out safer or more appropriate skills.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The manifest description is very broad and overlaps with common software help requests, which can cause the skill to activate in situations beyond its narrow intended use. Over-broad activation increases the chance of misrouting user requests, overshadowing more appropriate skills, and causing untrusted workflow instructions to be applied in the wrong context.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The trigger keywords include generic terms like 'testing', 'regression', and 'quality', which are common across many unrelated developer requests. This makes accidental invocation more likely and can route users into a workflow that assumes a unit-test coverage problem when that may not be the actual need.

Vague Triggers

High

• Confidence: 96% confidence
• Finding: The example trigger phrases are written as everyday, highly reusable requests that can match a wide range of benign software conversations, making activation overly permissive. Because examples often strongly influence routing behavior, these broad examples can substantially expand the effective scope of the skill and increase incorrect or unsafe dispatch.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The skill description and activation conditions are broad enough to match many ordinary software discussions, which can cause the skill to activate outside its intended scope. Over-broad triggering increases the chance of inappropriate delegation, irrelevant guidance, or prompt-surface expansion where the skill influences tasks it was not meant to handle.

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: The keyword list in the trigger section is underspecified and lacks contextual constraints, so common terms like testing, regression, or quality may activate the skill in many unrelated contexts. This can lead to accidental invocation, reduced routing precision, and increased exposure of downstream instructions to requests that do not actually need this capability.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The default prompt contains a very broad natural-language trigger covering common software activities like unit tests, testing, and analysis. In combination with skill routing, this can cause the skill to activate in situations the user did not explicitly intend, increasing the chance of unintended prompt injection exposure or inappropriate tool behavior.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: Enabling implicit invocation without tight constraints allows the platform to auto-select this skill from ordinary user language. That broadens the attack surface because adversarial or irrelevant conversations may invoke the skill unexpectedly, leading to context leakage, unsafe instruction following, or user confusion about which behavior is active.

Vague Triggers

High

• Confidence: 91% confidence
• Finding: The trigger sentence is so broadly phrased that it can match ordinary user requests and activate the skill outside its intended scope. In an agent system, overly permissive activation can cause incorrect routing, hidden prompt influence, or unreviewed execution of skill-specific workflows when the user did not explicitly request them.

Vague Triggers

Medium

• Confidence: 89% confidence
• Finding: The trigger specification lacks clear boundaries on when the skill should or should not activate, making it ambiguous for dispatch systems and increasing the chance of false positives. Ambiguous activation is dangerous because it can let a low-privilege documentation skill shape responses in unrelated contexts, reducing predictability and creating opportunities for prompt-routing abuse.

VirusTotal

64/64 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.