ClawHub
Back to skill

Security audit

knowledge-graph-builder

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a coherent knowledge-graph generator, but its documented deployment step can expose an entire private vault over the network.

Install only if you are comfortable with the skill reading the selected knowledge-vault directory and generating an HTML graph. For viewing, prefer opening the HTML locally or serving a dedicated output directory on 127.0.0.1; do not run the documented 0.0.0.0 server from a private vault unless you have intentionally restricted network access.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill instructs users to run local Python scripts that read the vault, generate output files, and optionally use environment-resolved paths, but it declares no permissions. This creates a trust and transparency gap: an agent or user may invoke file read/write behavior without an explicit permission boundary, increasing the chance of unintended access or modification of local content.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill recommends starting an HTTP server bound to 0.0.0.0, which exposes the generated graph and potentially the surrounding vault directory to any reachable network client. Because the documentation frames this as a normal deployment step and only briefly mentions firewall configuration, users may unintentionally publish sensitive knowledge-base contents externally without understanding the exposure.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.