Security audit

Unit Test Coverage Helper

Security checks across malware telemetry and agentic risk

Overview

This is a testing-workflow helper with broad activation wording, but no hidden code execution, data collection, persistence, or privileged behavior.

Before installing, consider narrowing the trigger terms or disabling implicit invocation if you only want this helper used for explicit unit-test or coverage requests. The inspected skill itself appears documentation-only and purpose-aligned.

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 (7)

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The trigger sentences are generic and can cause the skill to activate in situations where the user only loosely mentions testing or workflows, increasing the chance of inappropriate routing or overuse. In an agent ecosystem, overly broad activation can lead to unintended instruction application, reduced user control, and confused delegation behavior even though the README does not contain direct code execution or privilege-escalation content.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The trigger phrases are broad natural-language prompts that can match many ordinary requests about testing, coverage, or workflows, which raises the chance of unintended skill invocation. In an agent system, accidental activation can route user requests into the wrong workflow, causing inappropriate actions, confusing outputs, or unexpected access to repository context and tooling.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger keywords include broad, commonly used terms such as "testing" and "quality," which can cause the skill to activate in situations only loosely related to unit-test coverage. In an agent system, unintended invocation can misroute user requests, create prompt-scope confusion, and increase the chance that this skill influences tasks it was not meant to handle.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The example trigger sentences use generic phrasing like "Help me" and "I need a practical workflow," which can train or bias routing toward invoking this skill for broad requests. That increases accidental activation risk and may cause the agent to select this skill when the user did not specifically ask for unit testing or coverage assistance.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The default prompt uses a very broad natural-language trigger phrase that overlaps with common user requests about software, testing, and coverage. In combination with agent routing, this can cause unintended invocation of the skill in ordinary conversations, expanding the skill's activation surface and increasing the chance of inappropriate context access or unexpected behavior.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: Enabling implicit invocation without clear trigger constraints allows the platform to auto-select this skill based on loosely related user text. Because this skill targets a broad software-development domain, accidental activation is more likely, which can lead to unnecessary prompt injection exposure, incorrect tool selection, or unintended processing of user/project context.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger phrase is so broadly worded that it can match ordinary user requests unrelated to this specific skill, causing the agent to invoke the skill in contexts where it was not intended. In a testing/helper skill this is not directly code-execution dangerous, but it can lead to incorrect routing, prompt pollution, and reduced reliability of downstream security controls that depend on precise skill selection.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.