ClawHub
Back to skill

Security audit

测试用例生成专家

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only test-case generation skill whose flagged items appear to be documentation or quality issues rather than harmful behavior.

Install only if you want a Chinese-language test-case generation assistant. Review any sensitive requirements documents or links before providing them, since the skill is meant to analyze that user-supplied content.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (5)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 8)May include surrounding context.

md
---
AIGC:
    ContentProducer: Minimax Agent AI
    ContentPropagator: Minimax Agent AI
    Label: AIGC
    ProduceID: 84d544fd327b55cd0080c7c2b139803e
    PropagateID: 84d544fd327b55cd0080c7c2b139803e
    ReservedCode1: 3046022100c6c7714e7279d1884b14837b3c70895d7c4711cbe326b1d69201dcd4307b831e0221008d07c7a7925f8ecc32324fff65dc9f47817b2dd28580290662c610b9702c2c71
    ReservedCode2: 3046022100c02d6beb891f66ebbc7b23e684e75d5bb186684313ba1026617e15c14b082925022100cd6149d9ff1cf2e8e1c37229d1d8afd457abffca37546e51d54c8c2f83bf32cf
description: 测试用例生成专家技能。当用户提供产品需求文档、API链接、页面链接，或要求生成测试用例时触发。功能：多维度需求分析、系统化测试用例设计（等价类划分、边界值分析、决策表、状态转换、场景法、错�

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/templates.md (reported line 171)May include surrounding context.

md
| 小文件 | 极小文件(1字节) |
| 扩展名 | .exe, .bat, .sh(危险) |
| 双扩展名 | file.jpg.exe |
| 路径遍历 | ../../../etc/passwd |

---

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest-level Chinese-only output requirement removes user choice and can force responses into a language the user did not request or understand. In an agent system, this may degrade usability, hide important safety caveats, and create policy-compliance issues for multilingual deployments.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The usage section reinforces mandatory Chinese-only responses without opt-in, which can conflict with user instructions and platform language expectations. While not directly enabling code execution or data theft, it can impair transparency and safe user interaction.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger keywords are broad enough to activate the skill during ordinary conversation about testing, not only when the user explicitly requests test-case generation. This can cause unintended routing, override user intent, and increase the chance that unrelated content is treated as requirements input.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.