ClawHub
Back to skill

Security audit

Elective

Security checks across malware telemetry and agentic risk

Overview

This is a coherent PKU course-selection helper, but it gives agents sensitive login and enrollment authority without enough explicit user-control boundaries.

Review this skill before installing if you do not want an agent to access stored PKU credentials or act on course enrollment. Before using it, explicitly confirm the account, degree track, target course IDs, CAPTCHA backend, how long automation may run, and how to stop it or clear persisted sessions.

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 (2)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill explicitly documents sending CAPTCHA images to third-party OCR services but does not warn users that challenge data will leave the local system and be shared with external providers. In this context, the risk is elevated because the tool automates access to a real university enrollment system, so users may unknowingly expose session-linked challenge material or related metadata to untrusted services.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The documentation promotes auto-login using credentials sourced from the OS keyring and environment variables without clearly warning that the tool will access stored secrets automatically. This is dangerous because users or downstream agents may invoke the command expecting a passive status check or normal login flow, while the tool instead consumes sensitive credentials from local secret stores.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.