ClawHub
Back to skill

Security audit

Alumni Career Tracker

Security checks across malware telemetry and agentic risk

Overview

This skill is a local alumni career tracking tool that handles sensitive alumni data, but the access is disclosed, purpose-aligned, and not hidden or externally exfiltrating.

Install only if you are prepared to treat alumni data as sensitive. Use consented data, avoid storing individual salary or private notes unless necessary, restrict exported files, share aggregate reports where possible, and consider pinning dependencies in a controlled environment.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Context-Inappropriate Capability

Medium
Confidence
81% confidence
Finding
The documented `--update-linkedin` capability expands the skill from offline alumni analysis into external profile monitoring and data enrichment, which introduces privacy, consent, and scope-creep risks. Even if intended for benign record maintenance, automated collection or updating of LinkedIn-derived data can process personal information without clear authorization and may violate platform terms or institutional policy.

Description-Behavior Mismatch

Medium
Confidence
87% confidence
Finding
The skill can import and export raw alumni records, including potentially sensitive personal and career data such as names, organizations, locations, salary ranges, and notes. In the context of a skill described as analysis/guidance, this materially increases data exposure risk because it enables bulk extraction and ingestion of PII-like datasets beyond the minimum needed for the advertised function.

Unpinned Dependencies

Low
Category
Supply Chain
Content
dataclasses
pandas
rich
Confidence
95% confidence
Finding
pandas

Unpinned Dependencies

Low
Category
Supply Chain
Content
dataclasses
pandas
rich
Confidence
88% confidence
Finding
rich

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.