Back to skill

Security audit

AI测试工程师

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Chinese-language AI testing guidance skill, with one dashboard template that should be hardened before use with live or imported data.

Install only if you want a Chinese-language testing assistant. Treat outputs as templates for human review, avoid pasting confidential project data unless appropriate, and harden the dashboard template before connecting it to live systems or external data by rendering dynamic values as text rather than HTML.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
assets/templates/quality_dashboard.html:294
Finding

DOM-Based Cross-Site Scripting Through Unsanitized Dashboard Data

Content
View full analysis
` ${g.name} ${g.standard} ${g.actual} ${g.pass ? 'Passed' : 'Failed'} `).join(''); document.getElementById('quality-gates').innerHTML = gatesHtml; // Risk table if (data.risks.length > 0) { document.getElementById('risk-table').innerHTML = data.risks.map(r => ` ${r.name} ${r.level} ${r.status} `).join(''); } ``` The English words shown in this excerpt correspond to the Chinese display labels in the original template; the executable interpolation and `innerHTML` operations are unchanged. ### Technical Analysis The `updateDashboard(data)` function interpolates the following data fields directly into HTML strings: - `data.qualityGates[].name` - `data.qualityGates[].standard` - `data.qualityGates[].actual` - `data.risks[].name` - `data.risks[].level` - `data.risks[].status` The generated strings are assigned to `Element.innerHTML` without contextual encoding, sanitization, or schema validation. Consequently, HTML supplied through any of these properties is parsed as markup rather than displayed as text. The template currently initializes the function with static sample data. However, the source comment explicitly indicates that this data can be replaced by an API data source. If API responses, imported reports, defect descriptions, risk names, pipeline metadata, or other externally influenced values are passed to `update ...[truncated 2413 chars]
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (14)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

There is a clear description-behavior mismatch. The declared purpose presents a broad, full-lifecycle AI testing engineering skill collection with extensive capabilities across analysis, design, automation, execution monitoring, metrics, and specialized testing. In contrast, the supplied code only performs one narrow function: generating a Markdown-formatted test case template from user input, with static guidance for a few test types and priorities. It does not implement AI collaboration, automated case generation from requirements, test execution, monitoring, reporting, metrics, CI/CD integration, defect analysis, or a multi-module expert skill system. While the implemented function is related to testing and test case design, it materially underdelivers relative to the declared scope and primary purpose.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description lists many generic trigger terms such as '测试用例', '测试设计', '测试报告', and 'AI测试' as activation words. These are broad phrases commonly used in ordinary conversations about testing, and the file does not provide exclusion conditions or negative examples to clarify when the skill should not activate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The '触发指南' states the skill should load whenever the user expresses broad testing intents spanning strategy, design, automation, execution, metrics, and specialty testing. Because no scope limits, priority rules, or negative examples are given, this could cause unintended invocation for general testing discussions where this skill may not be the right fit.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The document declares lang="zh-CN", which hard-codes a specific locale for the skill output. Under the policy, forcing a language or locale without user opt-in or a clearly documented region-specific justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The code uses toLocaleString('zh-CN'), which forces Chinese date/time formatting for all users. This imposes a locale preference in the UI without offering a choice or documenting a justified regional constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file is written as an instructional skill reference in Chinese, beginning with a Chinese-only title and continuing entirely in Chinese. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation when no alternative language choice or locale justification is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

This markdown file is entirely written in Chinese, including headings, workflow instructions, and templates, with no indication that users may choose another language. Under the policy rule for language or locale, this is a natural-language constraint that could exclude users unless the locale restriction is explicitly justified or optional.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

Line L025 explicitly sets the output language to Chinese as a fixed requirement. This is a natural-language locale policy issue because the file does not present this as optional, user-selected, or justified by a region-specific purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire skill document is written in Chinese and provides no indication that users may choose another language or locale. Under the policy for natural-language constraints, forcing a specific language without user opt-in is a reportable issue unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file title and all instructional content are written in Chinese, which imposes a single language for operation guidance without any stated opt-in, alternative locale, or justification for a region-specific audience. Under the policy for natural-language violations, forcing one language without user choice is reportable across all file types.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The title and all instructional content in this markdown file are written in Chinese, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific context. This can violate a language/locale policy when a skill implicitly forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This code file contains natural-language strings that force a specific language/locale for interaction, including the module description and all prompts. Under the policy, locale constraints should either be optional for the user or clearly justified as region-specific; neither is present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The CSV template headers, sample titles, and explanatory text are entirely in Chinese, which constitutes a natural-language locale constraint visible in the file content. There is no indication that the template is intentionally region-specific or that users may choose another language, so this may violate language/locale policy requirements.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file contains natural-language instructions exclusively in Chinese, and nowhere indicates that the user may choose another language or that the content is intentionally limited to a Chinese-speaking audience. Under the language/locale policy, forcing a specific language without opt-in can be a policy concern.

Content

No source excerpt is available for this finding.