ClawHub
Back to skill

Security audit

team-memory

Security checks across malware telemetry and agentic risk

Overview

This skill is a simple, user-directed team memory integration, but users should treat the team profile data they store in it as potentially sensitive.

Before installing or using this skill, confirm your organization permits storing team-member profile information in BlueColumn, use non-sensitive or minimized descriptions where possible, and avoid uploading private HR, performance, health, or confidential workload details unless you are authorized to do so.

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
97% confidence
Finding
The skill explicitly demonstrates sending identifiable team-member information, strengths, weaknesses, communication preferences, and workload-related context to a third-party API endpoint without any privacy notice, minimization guidance, or consent requirements. This creates a real risk of exposing employee personal/professional profile data to an external service, which can violate internal confidentiality expectations and potentially trigger privacy, HR, or compliance issues.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.