github-mpc

Security checks across malware telemetry and agentic risk

Overview

This is a transparent setup guide for MCP integrations; it involves sensitive credentials, but the behavior is disclosed and fits the stated workflow.

Install only if you intend to configure this Product Guide Writer workflow for the named Trading212 systems. Use least-privilege or fine-grained GitHub and Atlassian access where possible, do not paste tokens into chat or logs, verify the MCP package names and endpoints, and enable optional Figma or Elasticsearch integrations only when needed.

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: 89% confidence
Finding: The skill tells users to create a GitHub personal access token and export it as an environment variable, but provides no guidance on credential sensitivity, least-privilege scopes, secure storage, rotation, or avoiding exposure in shell history and logs. In a setup-oriented skill for external integrations, this omission can lead users to handle long-lived credentials insecurely, increasing the chance of token leakage and unauthorized repository or organization access.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal