ClawHub
Back to skill

Security audit

vimeo

Security checks for vulnerabilities and agentic risk

Overview

This Vimeo skill is a disclosed Maton-based integration with higher-risk automation features that are documented with user-approval and scoping safeguards.

Before installing, be aware that ordinary Vimeo API use is straightforward, but automation features can run hosted code or continuously forward event data. Only authorize the Vimeo connection and any trigger or destination after confirming the exact account, resource, destination host, data fields, and whether the automation should persist.

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 (2)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The Vimeo skill package includes a full Linear trigger reference, which introduces actionable cross-source automation instructions unrelated to the declared app scope. Even though the header says this does not widen scope, an agent consuming the skill may still use this content to act on Linear events, creating scope confusion and enabling unintended access paths or data routing involving a different connected service.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file explicitly claims it does not widen the skill’s scope while simultaneously documenting concrete Linear event types, parameters, payloads, and forwarding guidance. That mismatch is dangerous because it can mislead downstream agents, reviewers, or policy checks into trusting the content as harmless reference text when it actually contains operational instructions for another integration and exposes sensitive payload structure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.