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 execution, persistence, credential handling, or destructive behavior found.

This skill appears safe to install for unit-test and coverage assistance. Review its broad activation terms if you prefer skills to run only on explicit requests, because it may be selected for general testing or quality prompts.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 so generic that it can activate on ordinary user phrasing unrelated to explicitly invoking this skill, causing over-broad routing and unintended execution. In an agent environment, ambiguous activation can lead to the wrong workflow being applied, unnecessary code/test generation, and increased exposure to downstream prompt-injection or misuse opportunities from unrelated requests.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentences are generic enough that the skill could be invoked by loosely related prompts, causing unintended activation and inappropriate steering of user interactions. In an agentic system, broad triggers can expand the skill’s operational scope beyond what the user clearly requested, increasing the risk of misrouting, confusion, or accidental execution in unsuitable contexts.
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 and can activate on generic requests about testing, workflows, or quality rather than a clear request to use this specific skill. Over-broad activation increases the chance of unintended invocation, which can cause irrelevant guidance, prompt-scope confusion, or hijack a user request that should have been handled by a different, more appropriate skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill description uses very broad activation terms such as software-and-data, testing, and implementation support, which can cause the skill to trigger outside its intended niche. Over-broad routing can lead to inappropriate skill selection, causing the agent to apply testing-oriented workflows to unrelated requests and reducing reliability or safety of downstream behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger keywords include generic terms like testing, regression, and quality that are ambiguous across many domains and software tasks. This increases the chance of false activation, which can misroute user requests and cause the assistant to follow the wrong operational workflow or provide mismatched guidance.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description and usage conditions are broad enough that the agent could invoke this skill for many ordinary software conversations that only loosely relate to unit testing or coverage. Over-broad activation creates unintended delegation risk: the skill may shape responses outside its intended scope, causing workflow hijacking, irrelevant guidance, or bypass of more appropriate specialized skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger keyword list includes generic terms like 'testing', 'regression', 'quality', and 'software-and-data', which overlap heavily with normal engineering discussions. This increases the chance of accidental invocation, letting the skill capture unrelated conversations and steer outputs inappropriately, reducing reliability and potentially masking safer or more relevant 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 uses broad, common request terms such as software, unit tests, test coverage, testing, regression, workflow, checklist, analysis, and implementation support, which can cause the skill to activate for many ordinary development queries without clear boundaries. This increases the chance of unintended routing, prompt-scope confusion, or the skill being invoked in contexts the user did not explicitly intend.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Enabling implicit invocation without a tightly scoped activation description allows the system to auto-select this skill based on vague overlaps with general engineering requests. In practice, this can produce over-invocation, interfere with user intent, and expand the skill's operational reach beyond narrowly defined test-coverage assistance.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The file list specifies separate English and Chinese instruction files, but the README does not state how the user's language preference is selected or whether language choice is optional. This can imply a locale/language behavior without explicit user opt-in.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The example trigger sentences are highly templated and generic, making activation plausible from ordinary conversation rather than clear intent to use this specific skill. While less severe than broad keywords, vague examples reinforce imprecise routing and can train or bias selection logic toward over-invocation.
Content: No source excerpt is available for this finding.