Security audit

Unit Test Coverage Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for helping with unit test coverage, with no hidden execution, persistence, or credential handling found.

This skill appears safe to install as a unit-test coverage helper. Users should be aware it may activate for broad testing or quality-related requests, so explicit invocation is preferable when multiple development skills are installed.

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

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger sentence 'Help me Teams need repeatable help adding useful unit tests and raising test coverage for existing codebases.' is overly broad and unnatural, increasing the chance that normal user language will accidentally activate this skill. In an agent routing context, ambiguous activation can cause the wrong skill to take control, leading to unintended processing of user requests or interference with more appropriate skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger sentence 'I need a practical workflow for Teams need repeatable help adding useful unit tests and raising test coverage for existing codebases.' remains ambiguous because the activation phrase is framed as a generic request pattern rather than a precise capability match. This makes misrouting more likely, especially in environments where many skills compete for selection based on loose semantic similarity.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are very broad and map common testing-related requests directly to this skill, which increases the chance of unintended invocation in unrelated contexts. Over-broad activation can cause the agent to apply the wrong workflow, leading to confusing outputs, unnecessary data exposure from extra context loading, or reduced reliability of downstream security controls that depend on precise routing.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The skill description uses broad activation terms such as 'software-and-data', 'testing', and 'regression', which can match many ordinary requests outside the narrow intended use case. Over-broad triggering can cause the wrong skill to activate, leading to irrelevant guidance, context hijacking, or accidental precedence over more appropriate skills in multi-skill environments.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The example triggers use very generic phrasing such as 'Help me...' and 'I need a practical workflow...', which makes reliable and safe activation difficult because they resemble normal conversation rather than clear invocation conditions. In a routing system, this can increase accidental activation frequency and misroute unrelated user tasks into this skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The skill description defines activation conditions too broadly, covering wide categories like software-and-data, unit tests, test coverage, testing, and regression without clear boundaries. In an agent environment, this increases unintended invocation risk, which can override more appropriate skills, mis-handle user intent, or expose the agent to unnecessary instruction-processing from unneeded skill content.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger keywords are very broad (software-and-data, unit tests, test coverage, testing, regression, quality) and overlap with many normal software conversations. This can cause the skill to activate outside its intended scope, creating unnecessary prompt injection surface and steering unrelated developer tasks into this skill’s workflow.
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 very broad, everyday-language terms like 'software-and-data', 'unit tests', 'test coverage', 'testing', 'regression', and 'implementation support', which can match a wide range of normal user requests unrelated to a narrowly scoped skill invocation. This increases the chance of unintended or over-eager activation, causing the agent to route user conversations into this skill 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: Implicit invocation is enabled even though the skill description and default prompt are broad, meaning the system may automatically invoke this skill without strong evidence that the user intended it. In practice, this can lead to prompt-routing mistakes, unnecessary exposure of project context to the skill, and interference with safer or more appropriate workflows.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrase is broad enough to match ordinary user language about testing and practical workflows, which can cause the skill to activate outside its intended scope. Over-broad routing can misapply the skill, override a more appropriate specialized skill, and increase the chance of unintended handling of unrelated requests.
Content: No source excerpt is available for this finding.