Security audit

Unit Test Coverage Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only helper for unit test coverage work, with no executable code, persistence, credential handling, or hidden data flow.

Installers should be aware that the skill may be selected for broad testing-related language. It is otherwise a straightforward unit-test coverage helper with no code execution or special access in the package.

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 (11)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger sentence is broad enough to match ordinary user phrasing such as 'help me' or 'I need a practical workflow,' which can cause the skill to activate in contexts beyond its intended scope. Over-broad activation increases the chance of prompt/skill routing errors, causing the agent to apply this unit-test workflow when the user asked for something else, which can suppress safer or more appropriate handling.
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 enough to activate on generic requests about testing, workflows, or implementation support without strong scoping. This can cause unintended invocation of the skill, leading to misrouting, overreach, or unnecessary access to user context, though the content shown does not itself contain direct code-execution or data-exfiltration behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger phrases are broad and generic enough that the skill may activate on ordinary conversations about testing, regression, or workflows rather than an explicit request to use this skill. Unintended invocation can cause incorrect tool/skill selection, context confusion, or unnecessary exposure of repository or code-related processing in situations where the user did not mean to invoke this helper.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The manifest description uses broad activation terms like 'software-and-data', 'testing', and 'implementation support', which can cause the skill to trigger for many generic engineering requests outside its intended scope. Overbroad routing increases the chance that this skill is invoked inappropriately, leading to irrelevant guidance, prompt-surface expansion, and possible interference with more suitable specialized skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger keyword list contains generic terms such as 'testing', 'regression', and 'quality' without scope constraints, making accidental activation likely. In a skill-routing system, this can siphon unrelated requests into this skill and broaden exposure to arbitrary inputs the skill was not designed to handle.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The activation description is overly broad and includes common software/testing terms without strong boundary conditions, which can cause the skill to be invoked for loosely related requests. In an agent system, unintended invocation can override more appropriate skills, expand the model's action surface, and lead to irrelevant or risky guidance being applied in the wrong context.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The keyword list contains broad terms such as testing, regression, and quality, which are common across many unrelated requests and lack disambiguating constraints. This increases the chance of accidental routing, making the skill activate outside its intended scope and potentially interfering with safer or more specialized handling.
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, everyday-language terms such as 'unit tests', 'test coverage', and 'testing', which can match many ordinary developer requests and trigger the skill unintentionally. Because implicit invocation is enabled, this increases the chance the agent will activate the skill in contexts where the user did not specifically request it, causing scope creep, confusing behavior, or unintended influence over responses.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: In this Chinese-language README, the core usage guidance and trigger phrases are written in English only, which can impose a language constraint on users without explicit opt-in or offering a locale choice. This may violate language/locale policy expectations for user-facing skill documentation.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The example trigger sentences use vague natural phrasing that mirrors ordinary requests and can train or encourage broad matching behavior. While less severe than the manifest and keyword issues, this still increases unintended invocation and weakens the boundary of when the skill should be selected.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The example trigger phrases are written as generic help requests that closely resemble normal user language, so they may match routine conversations rather than deliberate skill invocation. While this is less severe than unsafe code execution, it still weakens routing precision and can cause inappropriate skill selection.
Content: No source excerpt is available for this finding.