ClawHub
Back to skill

Security audit

ScreenshotOne

Security checks for vulnerabilities and agentic risk

Overview

This skill is mostly a normal ScreenshotOne connector, but its setup path tells the agent to install the required CLI by running an unverified internet script.

Before installing, verify the oo CLI through OOMOL's official installation process and avoid running remote installer scripts unless you trust that source. Confirm screenshot, animated, and bulk capture requests because they may send page content or supplied HTML/Markdown to the connector and may consume ScreenshotOne or OOMOL account credits.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (2)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill instructs the agent to install software by piping a remotely fetched script directly into bash, which is a classic supply-chain and remote-code-execution risk. If the install endpoint, transport, or upstream distribution is compromised, arbitrary code would execute on the host with the agent's privileges.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The action list describes take_screenshot as taking a screenshot from a URL, HTML, or Markdown source, which implies content generation/retrieval rather than modifying ScreenshotOne account state. However, the safety section says [write] actions change ScreenshotOne state and requires confirmation on that basis, creating a direct documentation contradiction about what the action does.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.