ClawHub

Cartogopher

Security checks across malware telemetry and agentic risk

Overview

CartoGopher’s skill instructions are coherent with setting up a vendor MCP code-intelligence tool, but users should understand it downloads vendor code, sends an email for a trial key, and stores an API key persistently.

Install only if you trust CartoGopher and are comfortable sending your email to cartogopher.com for a trial key. Inspect the downloaded bundle before running it, avoid modifying /etc/machine-id on production hosts unless you know it is needed, and consider storing the API key in a dedicated secret/config mechanism rather than a general shell profile.

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
96% confidence
Finding
The skill tells the operator to collect and transmit the user's email address to a third-party service to obtain a trial key, but provides no privacy notice, consent language, or explanation of how that personal data will be used. This creates a privacy and compliance risk because users may not realize their email is being shared with an external vendor for account creation or marketing-related follow-up.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The instructions append the API key directly into the user's shell profile, causing long-lived credential storage in plaintext on disk without a prominent warning. Persistent plaintext secrets are at risk from local compromise, backups, shell dotfile syncing, accidental sharing, and later disclosure when users inspect or publish their profile files.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal