ClawHub
Back to skill

Security audit

calculus-intelligent-grading

Security checks for vulnerabilities and agentic risk

Overview

The skill is a Chinese-language calculus grading demo whose network use is disclosed and purpose-aligned, but users should treat student submissions as data sent to DeepSeek.

Before using this with real coursework, confirm whether student answers, reference answers, and solution steps may be sent to DeepSeek, avoid including student identifiers where possible, and document any required consent or data-retention policy. Also note that the referenced demo HTML is not included in this package.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly states that student problem content and solution steps are sent to the DeepSeek API, but the documentation provides no user-facing notice, consent flow, or data-handling disclosure. In an educational grading context, submitted work may contain personally identifiable information or sensitive academic records, so silent third-party transmission creates a real privacy and compliance risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The description text is entirely in Chinese and presents the skill as a province-specific training tool, but it does not state that the Chinese-only locale is intentional nor offer any opt-in or alternative language option. This can be a natural-language policy issue when a skill effectively forces a specific language without user choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.