ClawHub
Back to skill

Security audit

The Scribble Thing

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently turns user-provided line-art images into scribe videos using a disclosed remote service, with consent and cleanup controls described.

Before installing, be comfortable with uploading artwork to the disclosed external service and with its current retention, terms, and pricing. Use only images you have rights to process, and treat the private management link as sensitive.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The default prompt is broadly phrased and does not communicate any limits on appropriate use, required user consent, or safety checks around the uploaded image and resulting animation workflow. In practice, this can cause the agent to invoke the external MCP service too eagerly whenever a user mentions line art or animation, increasing the chance of unintended data transfer to a third-party endpoint.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest advertises operations to create, monitor, unlock, download, and delete animations through a remote MCP endpoint, but provides no warning that user files and generated outputs may be transmitted off-platform or that destructive actions like deletion are available. This lack of disclosure makes accidental data exposure or unintended destructive actions more likely, especially because the skill handles user-supplied images and generated media.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.