Codegraph Tool

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent local code-indexing helper, with install and permission choices users should review before use.

Prefer the npx or npm installation path instead of the curl-to-sh command. Initialize CodeGraph only in repositories you are comfortable indexing, review exclusions such as .gitignore, and avoid optional auto-allow settings unless you are comfortable with the agent querying the code index without repeated prompts.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
95% confidence
Finding
The skill recommends piping a remotely fetched script directly into a shell (`curl ... | sh`) without any integrity verification, pinning, or safety warning. This creates a supply-chain execution path where a compromised repository, MITM in a misconfigured environment, or malicious update could lead to arbitrary code execution on the user's machine.

VirusTotal

55/55 vendors flagged this skill as clean.

View on VirusTotal