Security audit

Unit Test Coverage Helper

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only unit-test coverage helper with some overly broad activation wording but no hidden execution, persistence, credential handling, or exfiltration behavior.

Before installing, be aware that the skill may activate for broad software testing or quality requests, not only explicit coverage-improvement requests. It appears safe as a documentation/workflow helper, but users who rely on precise skill routing may want the publisher to narrow the triggers.

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 (9)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger sentences are highly generic ('Help me...', 'I need a practical workflow...') and can match ordinary user requests that are not specifically asking to invoke this skill. In an agentic system with automatic skill routing, this can cause unintended activation, context hijacking, or overshadowing of more appropriate skills, which may lead to incorrect actions or broadened access to project context.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger phrases are broad natural-language requests and even include a generic imperative form using the full demand statement, which increases the chance of unintended skill invocation. In an agent ecosystem, over-broad routing can cause the wrong skill to activate on ordinary testing-related conversations, leading to mis-execution, confusion, or bypass of more appropriate safeguards.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger keywords are broad enough to match many ordinary software-help requests, which can cause this skill to be invoked outside its narrow intended purpose. Over-broad activation is dangerous because it increases unintended routing, may override more appropriate specialist skills, and can expose users to irrelevant or lower-quality guidance in unrelated contexts.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The example trigger phrases use natural, everyday wording that is highly reusable across unrelated requests, making accidental invocation more likely. In this skill context, the risk is operational rather than code-execution-related: the agent may select this skill for vague requests and steer users into a testing workflow even when they did not ask for one.

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The trigger keywords include very broad terms like "testing" and "quality," which can match many ordinary software discussions unrelated to unit-test coverage. In an agent-routing context, this can cause the skill to activate too often, increasing the chance of irrelevant guidance, context hijacking, or accidental handling of tasks outside its intended scope.

Vague Triggers

Medium

Confidence: 83% confidence
Finding: The invocation condition is defined too broadly, saying the skill should be used whenever the user mentions certain topics or needs related support, without clear boundaries. This can lead to over-triggering on loosely related requests and reduce routing precision, which is a real security and reliability concern for agent systems that depend on correct skill selection.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The default prompt uses broad natural-language triggers like 'software-and-data', 'testing', and 'regression', which can cause the skill to be invoked in many ordinary conversations without clear user intent to use this specific capability. With implicit invocation enabled, this increases the chance of over-triggering, unintended context capture, and the agent steering users into this skill when it is not necessary.

Vague Triggers

High

Confidence: 95% confidence
Finding: The trigger sentence is phrased so broadly that ordinary user language could unintentionally activate this skill, causing it to engage outside its intended scope. In an agent environment, ambiguous activation boundaries can route unrelated requests into this skill and produce irrelevant or unsafe behavior chains, especially when multiple skills compete for similar phrasing.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger section lacks clear boundaries for when the skill should and should not activate, making the routing logic overly permissive. This can lead to accidental invocation on generic software requests, reducing reliability and potentially bypassing more appropriate specialized skills or safety checks elsewhere in the system.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.