Security audit

Unit Test Coverage Helper

Security checks across malware telemetry and agentic risk

Overview

This is a simple unit-test coverage workflow skill with overly broad activation wording but no hidden execution, persistence, credential access, or destructive behavior.

Before installing, be aware that the skill may activate on broad testing or quality requests. It appears safe for unit-test and coverage assistance, but users may want tighter trigger wording if they only want it invoked for explicit unit-test coverage work.

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 (8)

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The trigger sentences are excessively generic and can match a wide range of ordinary user requests, causing the skill to activate outside its intended scope. In an agent system, this can lead to inappropriate routing, instruction shadowing, or accidental insertion of workflow guidance into unrelated tasks, which increases the chance of unsafe or confusing behavior even though the content itself is not overtly malicious.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger phrases are broad enough to match many ordinary software requests, which can cause this skill to activate when a user did not explicitly ask for it. Over-broad activation increases the chance of unintended instruction injection into unrelated conversations and can steer the agent into unnecessary file analysis or code-generation workflows.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger keywords are broad enough to match many ordinary software-assistance requests, which can cause the skill to activate outside its intended context. While this is not a code-execution issue, overbroad invocation can route users into an unintended workflow, increasing the chance of irrelevant guidance, prompt-surface expansion, or misuse in contexts the skill was not designed to handle.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The example trigger phrases use generic language like 'Help me' and 'I need a practical workflow', which may encourage accidental invocation when users are making broad requests rather than explicitly seeking this skill. In a skill-routing system, such ambiguity can degrade boundary control and cause unnecessary or inappropriate skill selection.

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The trigger keywords include very broad terms such as "testing" and "quality", which commonly appear in ordinary software conversations unrelated to this specific skill. That increases the chance of accidental activation, causing the agent to apply the wrong workflow or introduce irrelevant test-coverage guidance when the user intended a different task.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The description says to use the skill when users ask for broad categories like "software-and-data" and several general testing-related topics, without defining clear scope limits. In an agent-routing context, overbroad activation can misroute requests, override better-matched skills, and create unsafe or low-quality task handling through unintended invocation.

Vague Triggers

Medium

Confidence: 83% confidence
Finding: The default prompt is phrased very broadly around common software activities like unit tests, testing, and coverage, which can cause the skill to be invoked in many ordinary conversations beyond the user's explicit intent. Because implicit invocation is enabled, this increases the chance of unintended routing, context leakage into the skill, or user confusion about which agent is acting.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The trigger sentence is so generic that it can match ordinary user requests about testing or practical workflows, causing the skill to activate outside its intended scope. Overly broad activation increases the chance of prompt/skill routing hijacks, unintended behavior, and interference with more appropriate skills in unrelated conversations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.