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 some broad activation wording but no hidden code, persistence, credential handling, or destructive behavior.

Before installing, be aware that the skill may activate on broad testing or quality requests. It appears safe from a security standpoint, but its triggers should ideally be narrowed to explicit unit-test or coverage-improvement requests.

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: 95% confidence
Finding: The trigger sentences are highly generic and can match broad, common user requests about testing, workflows, or implementation support, causing the skill to activate outside its intended scope. Overbroad activation increases the chance of prompt-routing mistakes, where this skill's instructions or assumptions are applied to unrelated requests and may interfere with safer or more appropriate handling.
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 to match many ordinary software-help requests, which can cause this skill to activate in situations where it was not specifically intended. Overbroad activation increases the chance of unnecessary context capture, incorrect tool/workflow application, and interference with more appropriate skills, reducing trust and potentially amplifying unsafe or low-quality outputs.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The manifest description contains very broad activation language such as 'Use when a user asks for software-and-data, unit tests, test coverage, testing, regression,' which can cause the skill to trigger on many generic engineering requests beyond its intended scope. Over-broad routing increases the chance this skill is selected when a narrower or safer skill should handle the request, leading to misapplication, prompt-surface expansion, and reduced control over agent behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The example trigger sentences use everyday phrasing that is so general it can match loosely related user requests, reinforcing over-activation of the skill. Because trigger examples often influence routing heuristics, broad examples can unintentionally steer unrelated conversations into this skill, increasing the risk of incorrect tool/skill selection.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The skill is documented only in Chinese and does not provide language-selection behavior or clarify whether outputs should match the user’s language. In multilingual environments this can cause misunderstanding of scope, incorrect use by non-Chinese operators, or mismatched responses that reduce safety and reliability.
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 applicability using a wide set of broad categories and request types, but does not clearly limit when the skill should not be used. This can lead to accidental selection for loosely related software tasks, producing mis-scoped assistance and increasing operational error in agent orchestration.
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 broad, common terms such as "testing" and "quality", which can cause the skill to be invoked in contexts far outside unit-test coverage work. Over-broad activation increases the chance of unintended routing, irrelevant guidance, or interference with more appropriate skills handling the user’s request.
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 broadly enough that normal user requests about software, tests, or implementation help could trigger this skill without the user explicitly intending to invoke it. Because implicit invocation is enabled, this increases the chance of over-selection, unintended prompt injection surface, and accidental application of the skill in contexts where its instructions or behaviors are not appropriate.
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 overly broad and includes generic language like 'Help me' and 'I need a practical workflow,' which can cause the skill to activate in contexts far beyond unit-test coverage assistance. Overbroad activation increases the chance of inappropriate routing, prompt hijacking via accidental invocation, and user confusion, especially in multi-skill agent environments.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.