ClawHub
Back to skill

Security audit

College Prep Tracker

Security checks across malware telemetry and agentic risk

Overview

This is a local college-application tracker whose data storage is purpose-aligned, but users should treat the saved student and financial-aid details as sensitive.

Install only if you are comfortable saving college-prep records locally in college-data.json. Avoid entering SSNs, tax documents, FAFSA login credentials, unnecessary private notes, or full sensitive essay drafts, and review or delete the data file when it is no longer needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill persistently stores sensitive educational and potentially family-related data, including student identities, academic records, application status, recommendation details, and financial aid information, in a local JSON file without clearly warning users that this information will be retained. In the skill context, this increases privacy risk because users may disclose minors' data assuming the interaction is ephemeral, and the accumulated file becomes a concentrated source of sensitive personal information if accessed by other local processes or users.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The eval explicitly expects the skill to write to `college-data.json`, which implies persistent modification of user-related data without any mention of confirmation, authorization, or safe handling. In a college-prep context this data includes student academic and extracurricular information, so silent writes increase the risk of unintended data storage, overwrites, or privacy issues if the agent acts without clear user consent.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.