ClawHub
Back to skill

Security audit

unbounce

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed Unbounce integration that uses Maton OAuth/API tooling and gives clear approval rules for writes, credentials, automation, and forwarding.

Install only if you intend to use Maton as the gateway for Unbounce. Review OAuth scopes, approve every write or automation step separately, avoid third-party trigger destinations unless you understand the ongoing data flow, and do not expose Maton API keys or stored credentials.

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 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest says this skill is for Unbounce API integration and explicitly states that Unbounce is not an event source; files under references//triggers.md are shared platform reference text and do not add Unbounce capability. This file, however, documents HubSpot event types and payloads inside the Unbounce skill package, which creates a description-behavior mismatch by presenting non-Unbounce automation capabilities within the skill's documented surface.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.