ClawHub
Back to skill

Security audit

TencentCloud QuestionMark OCR

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Tencent Cloud OCR exam-marking wrapper, with expected cloud credential use and external processing of user-provided exam images.

Install only if you intend to send exam images, PDFs, handwritten answers, and related results to Tencent Cloud for OCR/marking. Use Tencent Cloud credentials with the minimum permissions needed, avoid shared environments for secrets, and confirm you have permission to process any student or personal data through this service.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
85% confidence
Finding
The skill documents use of environment variables containing Tencent Cloud credentials, but it does not declare an explicit tool scope or permission boundary. That omission can cause the runtime or operator to expose secrets more broadly than necessary, reducing auditability and increasing the risk of unintended credential access by the skill or adjacent components.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill processes exam images, handwritten answers, and potentially student data, yet it does not clearly warn that the image content or referenced URLs will be transmitted to Tencent Cloud OCR services for processing. This is dangerous because users or integrators may unknowingly send sensitive educational or personal data to a third-party service without informed consent, creating privacy, compliance, and data handling risks.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The script sends user-supplied images or PDFs to Tencent Cloud OCR for processing, which is an external data transfer of potentially sensitive student content. In a skill context, this is expected functionality, but the absence of an explicit disclosure or consent prompt means users may unknowingly transmit personal, educational, or handwritten data to a third party.

Missing User Warnings

Low
Confidence
83% confidence
Finding
这是一个代码文件，适用 SQP-2。代码读取 TENCENTCLOUD_SECRET_ID 和 TENCENTCLOUD_SECRET_KEY 用于云端调用，虽然 docstring 列出了所需环境变量，但没有用户可见的安全提示说明脚本会使用这些凭证访问外部账户资源并可能产生费用。对凭证和计费资源的使用缺少明确披露。

Static analysis

No suspicious patterns detected.