ClawHub
Back to skill

Security audit

calculus-intelligent-grading

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent calculus grading demo that discloses its use of DeepSeek for AI grading, with privacy considerations users should manage before using real student work.

Before installing or using this with real coursework, confirm that students or administrators approve sending submissions to DeepSeek, remove identifiers where possible, and document retention and privacy handling. For training demos with synthetic examples, the described behavior is consistent with the stated purpose.

SkillSpector

By NVIDIA
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 (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly states that student grading content is sent to the DeepSeek API, but the document provides no user-facing disclosure, consent flow, or data-handling notice. In an educational grading context, submitted work can contain student identifiers or sensitive academic records, so silent third-party transmission creates a real privacy and compliance risk.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.