Back to skill

Security audit

Fuzzy Multi Agent Team

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent multi-agent orchestration skill with disclosed risks around spawning sub-agents, optional persistent sessions, and shared workspace files.

Install this only if you want agents to spawn and coordinate sub-agents. Prefer one-shot runs, avoid persistent sessions unless needed, keep shared state in explicit project files, and review any workspace writes from sub-agents before relying on them.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger description is extremely broad and includes generic phrases like "parallel agents," "multi-agent," and "coordinated agents," which can cause the skill to activate in contexts where the user did not explicitly request agent spawning. In a skill that can create multiple sub-agents and orchestrate file access, unintended activation increases the chance of unnecessary delegation, excess resource use, and unexpected actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly instructs agents to update shared workspace files but does not warn that sub-agents may modify user data or require confirmation before doing so. In a multi-agent orchestration skill, shared-file writes are more dangerous because several agents may concurrently change common state, causing unintended edits, corruption, or propagation of incorrect data across the team.

Content

No source excerpt is available for this finding.