ClawHub
Back to skill

Security audit

N-central Admin

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed N-central administration guide with high-impact endpoint operations, but its scope and safety flow are coherent with that purpose.

Install only for agents/operators you trust to administer N-central. Before using it on production tenants, require explicit customer/site/device scope, confirm target counts, use pilot runs, keep audit notes, and reserve command, patch, backup/export, registry, file, service, and process actions for authorized maintenance or incident workflows.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This section documents powerful endpoint-management capabilities such as service control, process termination, registry access, command execution, file system management, and task execution without any caution about operational risk, authorization, or change-control requirements. In an admin skill for N-central, omission of warnings can normalize unsafe use of destructive actions and increase the chance of accidental service disruption or misuse against managed devices.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The patch exception and backup incident workflows instruct users to launch patch tasks and trigger backup/export tasks but do not mention that these operations may consume resources, alter device state, interrupt services, or have tenant/data-handling implications. Because this skill is specifically for administrative use in a live RMM environment, the lack of warnings makes unsafe execution more likely during routine troubleshooting.

Content

No source excerpt is available for this finding.

Scope Creep

Low
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Content

Scanner excerpt · SKILL.md (reported line 17)May include surrounding context.

md
2. Confirm targeting (filter preview or explicit devices).
3. Apply change (rule/task/template/action).
4. Validate on a small sample of devices.
5. Expand scope only after validation.

## Read references only as needed

Static analysis

No suspicious patterns detected.