ClawHub
Back to skill

Security audit

Servicenow Docs

Security checks across malware telemetry and agentic risk

Overview

The skill mostly matches a ServiceNow documentation helper, but one article-fetching tool can be directed to fetch arbitrary URLs.

Review this skill before installing in environments with access to private networks or sensitive internal services. Prefer a version that restricts article fetching to HTTPS ServiceNow documentation domains or to URLs returned by the search tool.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
79% confidence
Finding
The skill clearly relies on multiple outbound network-backed tools and APIs, but the skill metadata does not declare corresponding permissions. Undeclared network capability weakens security review and policy enforcement because consumers may invoke a skill that can reach external services without that access being explicitly surfaced. In this context the destinations appear documentation-related and public, so the issue is more about transparency and control than obviously malicious behavior.

Context-Inappropriate Capability

Medium
Confidence
97% confidence
Finding
The article fetch tool exposes a user-controlled `url` parameter directly to `fetch()` with no hostname allowlist, scheme validation, or path restriction. In an agent/tooling context, this enables server-side request forgery behavior and allows the skill to make outbound requests beyond its stated purpose of retrieving ServiceNow documentation, potentially reaching internal services or arbitrary third-party endpoints depending on network placement.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
This tool performs an outbound network request to an arbitrary user-supplied URL without warning, validation, or scope controls. Even if intended for documentation retrieval, the actual behavior lets users repurpose the skill as a general fetch primitive, which increases exfiltration and SSRF risk in environments where the agent has broader network access than the user.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.