Security audit

Unit Test Coverage Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only unit test coverage helper with some broad auto-invocation wording but no hidden code, persistence, credential handling, or destructive behavior.

Installers should be aware that this skill may be invoked automatically for broad testing or quality requests. It is otherwise a local, documentation-only helper; use it when you want unit-test or coverage workflow assistance, and review any generated code changes as you normally would.

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 written as a highly generic natural-language phrase ('Help me...') that overlaps with ordinary user requests. This can cause the skill to activate unintentionally in unrelated conversations, leading to prompt/skill routing errors, irrelevant guidance, or displacement of more appropriate skills; in agent systems, overly broad activation logic increases the attack surface for prompt steering and misrouting.
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 repetitive enough to match ordinary user requests about testing, coverage, or workflows, which can cause the skill to activate outside a clearly intentional opt-in. In an agent setting, overly broad activation increases the chance of prompt-routing mistakes, unintended context capture, or the skill shaping responses when the user did not explicitly request it.
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 enough to activate on many ordinary software-help requests, which can cause this skill to run when the user did not explicitly ask for it. Over-broad activation increases the chance of unintended prompt injection surface, mis-scoped behavior, or workflow hijacking in multi-skill environments.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill description is broad enough to match many ordinary software-help requests, which can cause the agent to invoke this skill outside its intended scope. Over-broad routing increases the chance of inappropriate tool selection, context capture, or unreviewed code/test guidance being applied where a narrower skill or direct handling would be safer.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger examples use vague, everyday phrasing that does not meaningfully constrain when the skill should activate. This makes accidental or excessive invocation more likely, which can degrade agent behavior and expose users to irrelevant or over-privileged workflow guidance.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: 该技能的描述将触发范围定义为较宽的主题集合（如 software-and-data、testing、regression），但缺少明确的边界、优先级和排除条件，容易在仅部分相关的请求中被误触发。误触发本身不一定导致直接安全破坏，但会造成代理选择错误技能、偏离用户意图，进而影响结果可靠性，尤其在多技能编排环境中更明显。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: 关键词列表包含多个高度泛化词汇，如 testing、regression、quality，这些词在大量无关或仅弱相关的软件场景中都会出现，因此会显著提高误匹配概率。若代理仅基于关键词路由，该技能可能在不适合的任务上被调用，导致输出偏题、覆盖其他更合适的技能，属于提示/路由层面的真实风险。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The default prompt is phrased so broadly that it can match ordinary user requests about software, testing, or coverage, increasing the chance the skill is invoked when the user did not explicitly request it. In an agentic environment, this can cause unintended context injection, unexpected behavior, or over-application of the skill to unrelated development tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: Enabling implicit invocation without strict trigger boundaries or exclusion conditions allows the platform to auto-activate this skill during common developer conversations. That raises the risk of unrequested prompt insertion, context hijacking, or accidental use in situations where the skill's assumptions do not fit the task.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 76% confidence
Finding: The README explicitly labels one set of files as English and another as Chinese, but does not indicate how a user chooses or opts into a language. This can be a locale-policy concern because the skill documentation appears segmented by language without a documented user-selection mechanism.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 76% confidence
Finding: This file is labeled as a Chinese README, but key instructional content including demand description, workflow description, keywords, and trigger phrases remains in English. That can create a language/locale policy concern because the skill documentation does not explicitly offer users a choice of language or explain the mixed-language requirement.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.