Security audit

Unit Test Coverage Helper

Security checks for vulnerabilities and agentic risk

Overview

This skill provides local unit-test and coverage workflow guidance, with some broad trigger wording but no hidden execution, persistence, credential use, or destructive behavior.

This skill is reasonable to install if you want help adding unit tests or improving coverage. Be aware it may activate on general testing or quality requests because its trigger wording is broad; invoke it explicitly for unit-test coverage tasks if you want predictable behavior.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger sentence begins with a very generic conversational phrase ('Help me ...'), which increases the chance that ordinary user requests will unintentionally activate this skill outside its intended scope. In an agent system, over-broad activation can misroute requests, override better-matched skills, or cause the agent to apply testing-oriented workflows when the user did not explicitly ask for this capability.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentence is overly broad and malformed, which can cause accidental or inappropriate activation of the skill for loosely related requests. In an agent-routing context, vague activation criteria increase the chance of misrouting user prompts, producing irrelevant guidance, and overriding more appropriate specialized skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger phrases are broad enough to match many ordinary software requests, which can cause the skill to activate outside its intended scope. In an agent system, overscoped activation can override safer or more appropriate workflows, leading to irrelevant guidance, excessive autonomy, or unintended handling of user inputs.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill description uses broad activation terms such as 'software-and-data', 'testing', and 'analysis', which can cause the router to invoke this skill for many ordinary engineering requests beyond unit-test coverage work. Over-broad routing is dangerous because it can mis-handle user intent, override more appropriate specialized skills, and create unintended data exposure or workflow execution in the wrong context.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 99% confidence
Finding: The example trigger begins with the generic phrase 'Help me', which is common across a huge range of user requests and does not meaningfully constrain invocation to this skill's intended scope. This increases the chance of accidental activation, leading to poor routing decisions and potentially causing the agent to apply testing-oriented instructions where they do not belong.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger description is overly broad and matches common software-development conversations such as testing, regression, and quality. This can cause the skill to activate in unintended contexts, increasing the chance that it overrides a more appropriate skill, injects irrelevant workflow guidance, or expands its access to user context without clear user intent.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The example trigger phrases are generic enough that ordinary requests could unintentionally invoke this skill. In a multi-skill agent environment, this increases prompt-routing ambiguity and can lead to inappropriate execution paths, especially when users mention practical workflows or testing in unrelated contexts.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt is broad and generic enough to match common software-help requests, which can cause the skill to be invoked in situations beyond narrowly scoped unit-test coverage assistance. Because implicit invocation is enabled, this increases the chance of over-triggering and unintended routing, which can expose users to irrelevant or overly authoritative testing guidance in contexts where the skill was not specifically requested.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The invocation examples do not clearly define what qualifies for activation and omit negative examples, making the skill easier to trigger in unintended contexts. While this is not code execution risk, it can degrade system reliability by causing ambiguous routing and user confusion.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: In a Chinese-language README, core descriptive and invocation content is presented in English, which can impose a language expectation on users without explicit opt-in or explanation. The file does not state that English is required, optional, or paired with a user-selectable language behavior.
Content: No source excerpt is available for this finding.