ClawHub
Back to skill

Security audit

Nginx Config Linter

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward local nginx configuration linter that only reads user-specified config files and reports findings.

Install only if you are comfortable running a local tool that reads the nginx config file or directory you point it at. Be careful with `--recursive` on broad directories, because nginx configs can contain sensitive paths or operational details, and `--strict` may fail CI when warnings are found.

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 (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
78% confidence
Finding
The skill documentation instructs the agent to read arbitrary nginx configuration files and recursively scan directories, which clearly requires file-read capability, yet no permissions are declared. This creates a transparency and policy-enforcement gap: an orchestrator or reviewer may treat the skill as lower risk than it actually is, and the recursive audit behavior can expand access beyond a single intended file. The mentioned network capability is not evidenced strongly in this file, but undeclared file access alone is a valid concern.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.