ClawHub
Back to skill

Security audit

ObjectRemover Video Object Ops

Security checks for vulnerabilities and agentic risk

Overview

This instruction-only skill is coherently focused on sending user-provided videos to a disclosed backend for AI object removal or extraction, with no local code execution or persistence.

Install only if you are comfortable sending the video, prompt text, source URLs, and session or API identity information to the ObjectRemover backend for processing. Avoid confidential or regulated media unless your organization has approved that service and its retention policy.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill directs users to upload video files or import assets by URL to a third-party backend (apiobjectremover.tokenlens.ai) but does not clearly warn that user content will leave the local environment and be processed remotely. This creates a real privacy and data-handling risk because users may submit sensitive media or internal URLs without informed consent, especially since the skill is presented as a seamless end-to-end workflow.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file describes guest sessions for unregistered users and later documents asset upload and processed output URLs, but it does not warn users that their video data and session identifiers will be transmitted to backend services. For markdown files, SQP-2 applies when the skill description omits warnings about behaviors that could affect user data, privacy, or system integrity.

Content

No source excerpt is available for this finding.