Back to skill

Security audit

Unit Test Coverage Helper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documentation-only helper for improving unit test coverage, with some broad activation wording but no hidden execution, persistence, credential handling, or data exfiltration behavior.

Installers should be aware that this skill may activate for broad testing or software-quality requests. It appears safe for normal unit-test coverage assistance, but users may prefer narrower trigger wording or explicit invocation to avoid accidental routing.

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
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
94% confidence
Finding

The trigger sentences are broad enough to match ordinary help-seeking requests such as 'Help me' or 'I need a practical workflow,' which can cause the skill to activate outside its intended scope. In an agent environment, over-broad routing can expose users to irrelevant instructions, prompt collisions, or unintended tool behavior, even though the content here is not overtly malicious.

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 ordinary requests about software, testing, or practical workflows, which can cause unintended invocation of the skill outside a user's explicit intent. In an agent system, that increases the chance of misrouting, prompt collision, or unnecessary exposure of the skill's instructions and behavior during normal conversations.

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 match many ordinary software-testing requests, which can cause the skill to activate when the user did not explicitly intend to invoke it. Over-broad invocation increases the chance of inappropriate routing, prompt-context pollution, or an agent following this skill instead of a more suitable one, which can degrade safety and reliability.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
99% confidence
Finding

Using the generic phrase 'Help me' in an example trigger overlaps with normal conversational language and can cause accidental invocation in unrelated contexts. This makes routing less predictable and may cause the agent to apply the skill when a user is simply asking for general assistance rather than requesting test-coverage support.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description defines activation using very broad categories like software-and-data, unit tests, test coverage, testing, and regression, which overlap heavily with ordinary developer conversations. This can cause the skill to trigger in contexts where the user did not explicitly request it, leading to scope confusion, irrelevant instruction injection, or unintended workflow steering.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The keyword list includes highly generic terms such as testing, regression, and quality, which are common in many unrelated engineering discussions. Overbroad keyword activation increases the chance of accidental invocation, causing the assistant to prioritize this skill's workflow even when a different tool, policy, or narrower skill would be more appropriate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The default prompt uses broad everyday-language terms such as software, unit tests, test coverage, testing, regression, workflow, artifact, checklist, analysis, and implementation support, which can match many normal developer requests. This increases the chance the skill is invoked when the user did not explicitly intend it, expanding the skill's influence over unrelated conversations and creating prompt-routing risk.

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 clear trigger constraints allows the platform to auto-select this skill based on ambiguous language. In combination with the broad prompt vocabulary, this can cause unintended activation and expose user inputs or steer responses through a specialized skill when a general assistant response would have been more appropriate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger sentence begins with a very broad conversational phrase ('Help me'), which can cause accidental invocation in unrelated requests that merely mention testing or coverage. In an agent setting, overly permissive triggers expand the skill's activation surface and can lead to incorrect routing, unintended execution, or prompt-context contamination from a skill that was not actually requested.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The file lists English and Chinese variants of the skill documentation, but the README does not explicitly state that users may choose their preferred language or locale. This can be interpreted as a language-handling policy gap because the available locales are documented without clear user opt-in guidance.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

Most user-facing instructional content in this file is presented in Chinese, while some content remains in English, and there is no natural-language statement offering the user a language preference or explaining that this locale is optional or region-specific. Under the policy, forcing a specific language without user opt-in can be a locale-policy violation.

Content

No source excerpt is available for this finding.