ClawHub
Back to skill

Security audit

Consul Service Deregister

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it says, but it can remove live Consul service registrations in batch without a strong confirmation or scoping requirement.

Install only if you intentionally want an agent to deregister Consul services. Use dry-run first, verify every service ID and Consul agent host, require a human confirmation before live execution, and use a least-privilege Consul ACL token scoped only to the intended environment.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill invokes a local Python script that performs shell execution and network operations against Consul agents, yet the manifest declares no permissions or capability boundaries. This creates a transparency and governance gap: an agent may perform destructive network actions without clear user/admin consent or policy enforcement, increasing the chance of unauthorized service deregistration.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger phrase "offline" is overly broad and can match many unrelated operational conversations, causing the skill to activate outside the user's actual intent. Because this skill performs destructive deregistration of services over the network, accidental invocation could remove healthy instances from Consul and disrupt service discovery.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation describes live deregistration, batch execution, replay of raw curl commands, parallel execution, and ACL-token-backed access, but it does not clearly warn that the action is destructive and affects remote infrastructure. In this context, the lack of a prominent warning and safety guidance materially increases the risk of operators or automated agents removing production service registrations unintentionally.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.