ClawHub
Back to skill

Security audit

Unit Test Coverage Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a benign testing-workflow skill, with a routing-scoping caveat because it allows broad implicit invocation.

Install this for unit-test coverage help, but be aware it may be invoked more broadly than ideal for generic testing or quality requests. Prefer explicit use when you want unit-test or regression-test support, and review any proposed code changes before applying them.

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

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger sentences are generic enough to match ordinary user requests about testing and workflows, which can cause unintended invocation of this skill in situations where a more specific or safer skill should apply. In an agent system, ambiguous routing increases the chance of prompt/skill misselection, potentially leading to incorrect actions, user confusion, or bypass of intended scope boundaries.

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 activate on generic requests about software, testing, or practical workflows, which can cause the skill to run outside its intended scope. Over-broad activation increases the chance of incorrect tool selection, irrelevant guidance, or prompt-routing abuse when an attacker intentionally crafts ambiguous requests to steer the agent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description uses very broad activation language like 'software-and-data' and common testing terms, which can cause the skill to be invoked for many generic engineering requests beyond unit-test coverage work. Overbroad routing increases the chance that this skill intercepts requests better handled by more specific skills, creating prompt-scope confusion and reducing reliability of downstream agent behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger examples use generic phrasing such as 'Help me' and 'I need a practical workflow,' paired with a long requirement sentence, which does not enforce strong boundaries around when the skill should activate. Generic examples can train routing or selection systems toward over-invocation, causing unintended use of the skill in ordinary requests that only loosely relate to testing.

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 trigger language are broad enough to match many ordinary software conversations, which can cause the agent to invoke this skill outside its intended scope. Over-broad activation is risky because it can override more appropriate skills or inject irrelevant testing workflows into unrelated tasks, reducing reliability and potentially exposing code context unnecessarily.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The 'trigger方式' section relies only on generic keywords and positive examples, without boundaries or negative examples. This makes accidental invocation more likely, especially for common terms like 'testing', 'quality', or 'software-and-data', which are semantically broad and likely to appear in unrelated requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The default prompt is extremely broad and includes generic phrases like 'help me' plus common software/testing terms, which increases the chance the skill will be invoked during ordinary conversations that were not meant to call this agent. Over-broad triggering can cause unintended routing, context leakage to the skill, or user confusion about which agent is acting.

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 trigger constraints allows the platform to auto-select this skill from loosely related requests, which raises the risk of accidental invocation and unnecessary exposure of user context. In a skill about software testing, the domain vocabulary is common enough that many benign engineering conversations could match, making unintended activation more likely.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger phrase is so broad and awkwardly templated that it can match ordinary user requests about tests, coverage, or practical workflows far beyond the intended scope. This can cause the skill to activate unintentionally, leading to prompt-routing errors, user confusion, and increased exposure to any risky behaviors or assumptions embedded in the skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

The README declares English and Chinese instruction and guide files, but it does not explain how the user's preferred language is selected or whether the user can opt in to a locale. Under the language/locale policy, locale behavior should be user-directed or explicitly justified rather than implicitly assumed.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The document is explicitly a Chinese-language user guide (README.zh-CN.md) but does not state that language selection is optional or user-driven. Under the policy, forcing a specific language without opt-in can be a natural-language policy issue unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.