Security audit

Unit Test Coverage Helper

Security checks for vulnerabilities and agentic risk

Overview

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

Safe to install for unit-test and coverage work. Be aware that its broad trigger terms and implicit invocation may cause it to activate for general testing or quality discussions, so use explicit skill selection or disable implicit invocation if you want tighter routing.

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 (9)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger phrases are broad and generic enough that the skill may activate for loosely related software requests, causing unintended invocation and over-collection of user context or steering the assistant into a preset workflow when the user did not clearly request it. In an agent environment, ambiguous activation boundaries increase the chance of prompt-scope confusion and accidental misuse of the skill beyond its intended testing and coverage domain.
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 broad enough that the skill may activate for generic requests about workflows, testing, regression, or software-and-data without clear user intent to use this specific capability. In an agent environment, ambiguous invocation can cause misrouting, unintended execution, or over-application of the skill to unrelated code tasks, which may expose project context or produce unsafe automated changes.
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 very broad activation language such as 'software-and-data', 'unit tests', 'test coverage', 'testing', and 'regression' without clear scope boundaries. In an agent-routing system, this can cause the skill to activate for many ordinary engineering requests, increasing the chance of unintended invocation, context capture, and downstream misuse of the skill outside its intended narrow purpose.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The keyword trigger list contains generic terms like 'testing', 'regression', and 'quality' plus example phrases that are effectively restatements of the broad requirement. This makes accidental or excessive routing likely, which is dangerous in multi-skill environments because the skill may intercept unrelated requests and produce actions or advice based on an incorrect task classification.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description defines activation using a very broad set of user intents, including general software and testing requests, without strong boundaries for when the skill should or should not engage. This can cause the agent to invoke the skill in unrelated developer conversations, leading to prompt-scope hijacking, reduced routing precision, and inappropriate application of testing workflows where they do not fit.
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 overly generic terms such as 'testing', 'regression', and 'quality', which substantially overlap with normal software engineering conversations. In an agentic environment, this increases the risk of accidental or excessive skill activation, creating opportunity for misrouting, context capture, and interference with more appropriate specialized skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The default prompt is overly broad and phrased in generic language, which increases the chance that the platform invokes this skill for loosely related requests rather than explicit user intent. In a testing-focused skill, unintended activation could cause irrelevant prompt injection into conversations, misroute user tasks, or expose repository/testing context to the wrong helper.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: Enabling implicit invocation without tight trigger constraints allows the skill to activate automatically based on vague semantic matches. Because this skill is meant to assist with software and test workflows, accidental invocation could interfere with unrelated requests, expand the skill's effective authority, and increase the attack surface for prompt-routing abuse or unintended data exposure.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentence is so generic that it can match ordinary user requests about tests, workflows, or implementation help that were not intended to invoke this skill. Over-broad activation can cause misrouting, unintended tool/skill execution, and increased exposure to prompt-injection or irrelevant automated actions in contexts where a narrower testing-specific skill should not have been selected.
Content: No source excerpt is available for this finding.