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 hidden code execution or persistence, though its trigger wording is broader than ideal.

Before installing, be aware that the skill may activate on broad testing-related prompts. It is otherwise a low-risk helper: it provides workflow guidance for unit-test coverage and does not ship executable code or request privileged access.

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

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentences are broad enough to match generic user requests about testing, workflows, or implementation support, which increases the chance that the skill is invoked when the user did not specifically intend to use it. Unintended invocation can steer conversations, expose irrelevant instructions, or cause the agent to prioritize this skill over a more appropriate one, reducing reliability and potentially amplifying any unsafe behavior present in the skill instructions.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger phrases are highly generic and include broad terms like 'unit tests', 'test coverage', and 'testing', plus templated phrases that can match many ordinary software requests. This can cause unintended skill activation, leading the agent to apply the wrong workflow or disclose irrelevant guidance in contexts where the user did not explicitly request this skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill description is broad enough to trigger on many ordinary software-engineering requests, including generic requests about testing, regression, or implementation help. Overly broad routing can cause this skill to activate outside its intended niche, leading to incorrect delegation, prompt-scope confusion, or unintended exposure of project context to a less appropriate skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The keyword list uses vague, high-frequency terms like 'testing', 'regression', and 'quality' that appear in many normal engineering conversations. In a skill-routing system, such broad triggers can cause accidental invocation and reduce trust in skill boundaries, which is a real security and safety concern when skills may have access to contextual data or produce authoritative workflow guidance.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill description is broad and ties activation to a wide family of software/testing requests rather than a narrowly scoped task. In agentic environments, this can cause unintended invocation on loosely related prompts, leading to irrelevant guidance, context hijacking, or interference with a more appropriate skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger keywords include very common technical terms like 'testing' and 'quality', which are likely to appear in many unrelated prompts. This increases the chance of accidental routing, causing the agent to select this skill when the user did not intend unit-test coverage assistance, reducing reliability and potentially exposing unrelated context to the skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The default prompt and description are broad enough to trigger on common testing-related requests, which can cause the skill to be invoked outside narrowly intended scenarios. Because implicit invocation is enabled, this increases the chance of overreach, context hijacking, or unnecessary exposure of user prompts to a skill that was not specifically requested.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The invocation section lacks concrete boundaries on when the skill should or should not run, and its examples overlap with many ordinary software-assistance requests. This increases the chance of misrouting user requests to this skill, causing inappropriate automation, noisy outputs, or unintended handling of repository-specific context under the wrong workflow.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

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 awkwardly constructed, making accidental invocation plausible when users ask for generic testing help. Overbroad triggers can cause the wrong skill to activate and steer the agent into irrelevant or unintended workflows, reducing reliability and potentially exposing unrelated context to the skill.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: This is a zh-CN README, but substantial user-facing content such as the demand description and trigger phrases remains in English. That can impose a language choice on users without stating whether bilingual output is intentional or user-selected.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The example trigger phrases are generic and lack guardrails, which reinforces overbroad matching behavior and makes it easier for unrelated user prompts to invoke the skill. While less severe than a broad description or keyword list, this still increases the chance of misrouting and inappropriate skill selection.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.