Security audit

Unit Test Coverage Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a simple unit-test coverage guidance skill with no executable payload, persistence, credential handling, or hidden behavior.

Install this if you want repeatable help planning or writing unit tests and coverage improvements. Be aware it may activate on broad testing or quality requests, so explicitly name another skill or clarify scope when you do not want unit-test coverage help.

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: 97% confidence
Finding: The trigger sentence "Help me Teams need repeatable help adding useful unit tests and raising test coverage for existing codebases" is broad and malformed enough that it can overlap with ordinary user phrasing, increasing the chance that the skill activates in unintended contexts. Unintended activation can steer unrelated conversations into this skill's workflow, causing misrouting, confusion, and possible suppression of a more appropriate skill or safer handling path.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger sentences are broad and templated enough that the skill may activate on generic requests about software, testing, or practical workflows rather than only when the user explicitly wants unit-test coverage help. Over-broad activation can cause incorrect tool selection, prompt-routing mistakes, or unintended disclosure of repository/testing guidance into unrelated conversations, though the content here is not directly harmful or privilege-seeking.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger phrases are generic and map to common software-testing terms, which increases the chance the skill is invoked in situations where the user did not explicitly intend to use it. In agent ecosystems, overly broad invocation can cause capability overreach, misrouting, or unintended exposure of repository context to the wrong skill, even if the skill itself is not overtly dangerous.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill description uses very broad invocation terms such as 'software-and-data' and generic requests for workflows, analysis, and implementation support, which can cause the skill to activate for many unrelated software tasks. Over-broad routing increases the chance that this skill is selected when a more appropriate or safer specialized skill should handle the request, leading to incorrect guidance or unintended task scope expansion.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger examples are phrased in broad, everyday language and effectively teach the router to invoke the skill for generic 'help me' or 'I need a practical workflow' requests tied only loosely to the requirement text. This can create accidental invocation and prompt hijacking of unrelated developer requests, reducing routing precision and potentially exposing users to irrelevant or lower-quality actions.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description and usage condition are broad enough to match many generic software requests, which can cause the skill to activate outside its intended scope. Over-broad activation is dangerous because it can steer unrelated conversations into this workflow, increasing the chance of inappropriate guidance, prompt interference, or masking a more suitable specialized skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The keyword list uses very broad terms such as 'testing' and 'quality' without contextual constraints, making accidental or excessive triggering likely. In an agent environment, loose trigger keywords can route user input incorrectly, causing the model to apply the wrong instructions or expose workflow logic in contexts where it does not belong.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt uses broad, natural-language triggers such as 'software-and-data,' 'unit tests,' 'test coverage,' 'testing,' and 'analysis,' which can cause the skill to activate in many ordinary development conversations without clear user intent. This increases the chance of unintended invocation, context hijacking, or overshadowing more appropriate skills, especially because implicit invocation is enabled.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The usage signals provide keywords and trigger sentences without clear scope boundaries or negative examples, making activation criteria ambiguous. This increases the risk of accidental invocation from loosely related software questions, which can degrade routing integrity and make system behavior easier to manipulate through prompt phrasing.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The example trigger phrases demonstrate invocation patterns but do not show any limiting conditions, which encourages matching on vague natural-language requests. This increases false activations and may cause the assistant to enter the skill flow when the user is only mentioning testing concepts casually rather than requesting targeted unit-test coverage help.
Content: No source excerpt is available for this finding.