ClawHub
Back to skill

Security audit

mufi-admin

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent admin workflow guide, but it enables persistent changes in a live-looking admin system without clear authorization, environment, or confirmation controls.

Install only if you are authorized to administer this MUFI environment and intend to create real events, campaigns, templates, and frames. Before use, confirm whether the target is production or test, review every record before saving, and avoid using an authenticated browser profile unless you are comfortable with the agent acting through that session.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill provides step-by-step instructions to create and link records in an admin interface that appears to be a live production system, but it includes no warning, confirmation gate, environment check, or requirement to verify authorization before making changes. Because it automates persistent admin actions across events, campaigns, templates, and frames, misuse or accidental execution could modify production data at scale and cause operational disruption or unauthorized content publication.

Static analysis

No suspicious patterns detected.