ClawHub
Back to skill

Security audit

compass-fpx

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Compass data-fetching helper that uses a browser bridge and local parsing script, with no evidence of hidden exfiltration or destructive behavior.

Before installing, confirm you are comfortable installing the fpx CLI and ContextMint Bridge extension, pairing it with a Compass browser tab, and letting the skill fetch Compass pages through that browser context. Review the extension and npm package provenance as you would for any tool that can use a browser 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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (1)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill clearly instructs the user to perform outbound network access via the fpx CLI and browser bridge, but it does not declare any explicit tool scope such as permissions or allowed-tools. That mismatch is risky because an agent or reviewer may not realize the skill requires network-capable tooling, reducing transparency and weakening enforcement of least privilege.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.