ClawHub
Back to skill

Security audit

Agent DNSTT Rendezvous

Security checks across malware telemetry and agentic risk

Overview

This skill is a local planning and verification helper for authorized DNSTT tunnel setup, with clear limits and no evidence of hidden execution or data exfiltration.

Install only if you intend to coordinate DNSTT on infrastructure you own or are explicitly authorized to administer. Review generated argv plans before running them, keep listeners loopback unless deliberately approved, protect the HMAC secret and private key, and remember that DNS tunnel metadata may be visible to resolvers and network operators.

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
92% confidence
Finding
The skill documentation describes capabilities that read environment variables, read and write local files, invoke shell commands, and coordinate network-related tunnel configuration, yet no explicit permissions declaration is present in the metadata. Even though the skill includes strong safety language and avoids auto-execution, the undeclared capability surface can mislead operators or downstream policy engines, reducing review quality and enabling over-privileged use in environments that rely on manifest-declared permissions.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.