ClawHub
Back to skill

Security audit

super-screenshot

Security checks for vulnerabilities and agentic risk

Overview

This is a screenshot-guidance skill with no executable code, persistence, credentials, or hidden data flow, though users should be careful not to capture sensitive screen content.

Install only if you want your agent to use local or browser screenshot tools when screenshot capture is relevant. Review captures before sharing them, because screenshots can unintentionally include private URLs, tokens, notifications, personal information, or internal data.

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
Confidence
88% confidence
Finding
The skill's trigger description is unusually broad and could cause the agent to invoke this skill for many loosely related screenshot, debugging, QA, or browser tasks without clear boundaries. While the content is not overtly malicious, over-broad routing can expand the skill's effective authority, leading to unnecessary tool use, capture of unintended content, or accidental exposure of sensitive on-screen information.

Static analysis

No suspicious patterns detected.