ClawHub
Back to skill

Security audit

Wayfront

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent Wayfront MCP query helper, with sensitive business-data access disclosed and controlled by the user's Wayfront token.

Install only in a Wayfront workspace where the MCP token is scoped to data the agent is allowed to query. Treat returned client, billing, support, team, log, template, and activity data as confidential, and review newly exposed MCP tools before using them for broad queries.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.

md
- Which actions it supports (`list` and/or `show`)
- Which fields are filterable and sortable

**This skill is schema-first.** New Wayfront MCP endpoints appear automatically — you don't need to update this skill. Always check the live schema for the authoritative field list and capabilities.

---

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill is designed to access sensitive business and client records such as tickets, invoices, subscriptions, and client identities, but it provides no privacy notice or guidance on handling confidential data. In practice, that increases the chance of overcollection, inappropriate summarization, or disclosure of customer and business information through routine use.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill explicitly advertises schema-first discovery where new MCP endpoints appear automatically, which means its reachable capability set can expand over time without a corresponding review of the skill text or user expectations. That creates scope-drift risk: future endpoints could expose more sensitive operations or data domains than the documented business-query use case, and the skill instructs the agent to trust the live schema as authoritative.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The documentation broadens access beyond core client/order/invoice data to logs, team accounts, templates, and user activity, which are more administrative and sensitive than the headline description suggests. This mismatch can lead an agent or user to query internal operational data they did not expect the skill to expose.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.