ClawHub
Back to skill

Security audit

Screenshot Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This is a simple screenshot-analysis skill with no executable code, persistence, or hidden authority, though users should avoid uploading sensitive screenshots.

Install only if you are comfortable sending uploaded screenshots/images for AI analysis. Crop or redact passwords, API keys, financial details, private messages, internal dashboards, browser tabs, notifications, and account identifiers before use.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description encourages users to upload screenshots and images but does not warn that those files may contain sensitive information such as personal data, credentials, internal dashboards, or confidential documents. In this context, omission of a privacy warning is meaningful because screenshots frequently capture more information than users realize, increasing the risk of inadvertent disclosure.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The example trigger phrases are generic enough to match ordinary image-related user requests, which can cause this skill to activate more often than intended. Because the skill processes user-uploaded screenshots and images, over-broad routing increases the chance that sensitive visual data is sent into the skill without explicit user intent or awareness.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.