ClawHub
Back to skill

Security audit

Twitter Monitor By Longge

Security checks across malware telemetry and agentic risk

Overview

The skill appears purpose-aligned for Twitter monitoring, but it asks for sensitive Twitter session cookies without enough handling or safety disclosure.

Review this carefully before installing. Only use it if you are comfortable giving the skill access to Twitter session cookies, store those values only in protected environment variables or a secrets manager, do not commit or paste them into logs, and prefer a version that uses official scoped API credentials or clearly documents cookie handling.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill advertises functionality that requires environment variables, network access, and shell execution, yet it declares no permissions or trust boundaries. This creates a transparency and consent problem: users may provide credentials and run the skill without understanding its effective capabilities, increasing the chance of unintended data exposure or misuse.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The documentation instructs users to provide Twitter authentication cookies (AUTH_TOKEN and CT0), which are sensitive session credentials, but it does not warn about their sensitivity, storage, handling, or the risks of reuse and compromise. In this context, the skill monitors Twitter and sends notifications over the network, so misuse or leakage of those cookies could allow account/session abuse and unauthorized access to the user's Twitter session.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.