ClawHub
Back to skill

Security audit

OceanToken Media

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed OceanToken media-generation integration that can spend user credits and save assets, but its behavior is coherent with that purpose.

Install this only if you intend to connect an OceanToken account and let the agent create media assets in your project. Review generation costs before approving larger jobs, and be careful when providing local reference images because they may be uploaded to OceanToken for editing or animation.

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
  • 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The default prompt and skill description are broad enough that the agent may invoke this media-generation skill for loosely related requests without explicit user intent. Because the skill can create and save project artifacts, unintended activation could cause unwanted content generation, accidental project modifications, or unnecessary use of connected external tools and credits.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.