Back to skill

Security audit

模型可执行测试用例生成器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Chinese-language helper for producing structured automation test-case JSON, with no evidence of hidden data access, persistence, or exfiltration.

Install this if you want Chinese-default structured JSON test-case generation. Review or override the locale/timezone defaults for non-Chinese projects, and keep production, payment, deletion, or irreversible test cases disabled unless explicitly authorized.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill instructs the agent to read local reference files and optionally run a local validation script, but it does not declare any explicit tool scope such as allowed files or permissions. In an agent system, undeclared file-read capability can expand the accessible trust boundary and make it easier for the skill to read unintended local files if later prompts or integrations misuse the skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill metadata and prompt are fully Chinese-language and imply a fixed output locale without indicating that language should follow user preference or task context. While not a direct exploit primitive, this can create operational and security review gaps if downstream agents, validators, or human reviewers expect another language, leading to misunderstood test steps, missed warnings, or improper execution.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The default prompt is broadly scoped and invites use whenever there are requirements, prototypes, API docs, or similar inputs, but it does not define boundaries, eligibility criteria, or exclusions. In an agentic environment, overly broad invocation criteria can cause the skill to be selected for ambiguous or sensitive tasks, increasing the chance of misuse, over-collection of context, or generation of unsafe test artifacts against unintended targets.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The title and entire instruction set are written as a Chinese-only playbook, with no indication that users may choose another language or that the skill is intentionally region-specific. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The document hard-codes locale as zh-CN and timezone as Asia/Shanghai in the default schema and repeats the same defaults in the standard example. This is a natural-language policy concern because it imposes a specific language/locale configuration by default without opt-in, alternative options, or a stated region-specific justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction '默认使用中文标题' sets a default language policy for generated content. Under the policy rules, forcing a specific language without explicit user opt-in can be a natural-language policy violation unless the locale constraint is clearly justified, which is not stated here.

Content

No source excerpt is available for this finding.