Security audit

Unit Test Coverage Helper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only helper for unit test coverage work, with no executable code or hidden persistence, though its automatic trigger scope is broader than ideal.

Installers should understand that this skill may activate automatically on broad testing or quality-related prompts. It is otherwise a low-risk documentation helper; review its output before applying any suggested code changes or test commands in a real repository.

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 is so generic that ordinary user requests about testing or practical workflows could activate this skill unintentionally, causing skill overreach and misrouting. In an agent system, broad activation criteria can let a skill intercept requests outside its intended scope, which may degrade correctness and create opportunities for prompt-surface abuse if the skill is invoked in inappropriate contexts.
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 extremely broad and can activate on common testing-related requests without clear boundaries or disambiguation. This increases the chance of unintended invocation, which can cause the agent to apply this skill in the wrong context, override better-matched guidance, or broaden the attack surface for prompt-routing abuse.
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 broad natural-language patterns such as 'Help me ...' and 'I need a practical workflow ...', which can match ordinary user requests and cause this skill to activate unintentionally. In an agent system, over-broad activation can route unrelated conversations into this skill, leading to incorrect handling, prompt hijacking surface expansion, or unexpected disclosure of repository-specific guidance.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger keywords are broad and generic for software work, so this skill may activate for many ordinary requests involving testing, regression, or quality even when the user did not intend to invoke it. That can cause unintended routing, reduce precision, and potentially override a more appropriate skill, though it does not directly introduce code execution or data exfiltration risk.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The example trigger phrases are highly templated and broad, effectively instructing invocation for a wide range of common requests without clear boundaries. In a skill-selection system, this increases the chance of accidental or over-eager activation, which can misroute user tasks and degrade safety or relevance of downstream assistance.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill description says it should be used when users ask about broad categories like software-and-data, testing, or regression, without enough boundary conditions. This can cause the skill to activate for a large volume of ordinary requests that are only loosely related, which is risky because it broadens the skill's operational scope beyond its intended purpose.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger keywords are broad and weakly scoped, especially terms like "testing" and "quality", which can match many unrelated user requests and cause accidental invocation of the skill. Over-broad routing increases the chance that the agent applies this skill in contexts where its workflow or assumptions are not appropriate, potentially leading to misrouting, confusion, or unintended handling of user tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The default prompt is phrased in broad, natural language terms such as 'help me' and general software/testing topics, which can cause the skill to be invoked for a wide range of ordinary requests. In combination with implicit invocation, this increases the chance of over-triggering, unintended routing, and the skill being selected outside a clearly bounded unit-testing context.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Enabling implicit invocation without a tightly scoped trigger definition allows the platform to auto-select this skill based on ambiguous requests. Because the skill covers broad concepts like testing, software, and practical workflow support, it may be invoked unexpectedly, leading to incorrect handling, user confusion, or interference with more appropriate skills.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 76% confidence
Finding: This is a Chinese README, but the explicit trigger phrases are presented only in English, which can amount to a language expectation without stating that users may invoke the skill in Chinese or choose their preferred language. There is no accompanying note offering a language choice or explaining that English phrasing is merely illustrative.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.