Security audit

Unit Test Coverage Helper

Security checks across malware telemetry and agentic risk

Overview

This skill is a documentation-only helper for adding unit tests and improving coverage, with some overly broad activation wording but no hidden execution or data-handling behavior.

Installers should understand that this skill may be invoked for broad testing or quality-related requests because implicit invocation is enabled. It appears safe as a unit-test coverage helper, but tighter trigger wording would reduce accidental use in unrelated conversations.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (10)

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger sentences are overly broad and awkwardly generic, making it likely the skill will activate for common requests that merely mention help or workflows rather than specifically requesting unit-test coverage assistance. In an agent ecosystem, this can cause inappropriate routing, unnecessary invocation, and expansion of the skill's influence beyond its intended scope, which increases the chance of unsafe or low-quality automated behavior.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger phrases are broad enough to match many ordinary requests about testing, coverage, and regression, which can cause the skill to activate outside its intended scope. In an agent system, over-broad activation can route unrelated user requests into this skill, increasing the chance of inappropriate instructions, wasted actions, or policy bypass through unintended tool selection.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The skill description is broad enough to match many ordinary software-help requests, which can cause the agent to invoke this skill outside its narrow intended use. Over-broad activation increases the chance of inappropriate context capture, user confusion, and routing away from more suitable skills or safer defaults.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The keyword list contains highly generic terms such as 'testing', 'regression', and 'quality' that commonly appear in normal engineering discussions unrelated to unit-test coverage. This makes accidental activation likely, which can degrade routing integrity and cause the system to apply the wrong workflow to unrelated requests.

Vague Triggers

Low

Confidence: 88% confidence
Finding: The example trigger sentences use vague, natural phrasing that does not establish clear activation boundaries, encouraging broad matching behavior. While not directly exploitable for code execution, they reinforce loose invocation semantics and increase the probability of unintended skill selection.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger description is broad enough to activate on many ordinary testing or regression-related requests, not just narrowly scoped unit-test coverage assistance. Over-broad routing can cause the wrong skill to handle user input, increasing the chance of inappropriate guidance, accidental context capture, or policy bypass through misclassification.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The keyword list uses highly generic terms like 'testing' and 'quality' without boundaries, making unintended invocation likely across many unrelated software requests. This weak trigger hygiene can be exploited indirectly by prompting the agent with broad terms to force this skill into contexts it was not designed to handle.

Vague Triggers

High

Confidence: 95% confidence
Finding: The default prompt is phrased so broadly that it can match common user requests about software, testing, or implementation support, increasing the chance the skill is invoked when the user did not explicitly intend to use it. In an implicitly invokable system, this can cause unintended context injection, over-broad routing, and unexpected execution of skill-specific instructions in unrelated conversations.

Vague Triggers

High

Confidence: 97% confidence
Finding: Enabling implicit invocation without tight activation constraints allows the skill to be auto-selected from ordinary developer conversation, even when the user did not request it directly. Because this skill is framed broadly around software, testing, workflows, and implementation support, unintended invocation can influence agent behavior, introduce unrequested actions or guidance, and expand the attack surface for prompt-routing abuse.

Vague Triggers

High

Confidence: 96% confidence
Finding: The trigger sentence is so broad and unnatural that it can match ordinary user requests about unit tests or practical workflows, causing the skill to activate outside its intended scope. Over-broad activation increases prompt-routing risk: the wrong skill may intercept benign conversations, inject irrelevant instructions, or crowd out a more appropriate and safer handler.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.