ClawHub

Framebuffer Dump

Security checks across malware telemetry and agentic risk

Overview

This skill performs the advertised STM32 framebuffer capture workflow, with privacy and scoping cautions but no evidence of hidden, destructive, or exfiltrating behavior.

Install only if you intend to let the agent read the connected STM32 device framebuffer through J-Link. Verify the target device, framebuffer address, size, and output paths first; use a private temporary directory when possible and delete raw dumps, PNGs, and logs after use if the screen may contain sensitive information.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill instructs reading local files and generating output artifacts, but the manifest does not declare any permissions. That creates a transparency and policy-enforcement gap: users and the platform may not realize the skill can access filesystem paths, logs, templates, and dumped framebuffer binaries, increasing the chance of unintended data exposure or unauthorized file access.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The README instructs users to dump the live device framebuffer and save the raw dump and PNG to disk, but it does not warn that the screen contents may contain secrets, personal data, credentials, or other sensitive operational information. In an agent-skill context, this omission is more dangerous because the workflow is positioned for easy automation ('The agent will handle the full workflow automatically'), increasing the chance of unattended collection and persistence of sensitive images.

Vague Triggers

Medium
Confidence
86% confidence
Finding
The manifest uses broad trigger terms like 'export', 'snapshot', 'dump', and 'capture', which can match common user requests outside the narrow hardware-debugging context. This increases the risk of accidental invocation of a skill that reads device memory and writes local artifacts, potentially exposing on-screen sensitive information when the user intended a generic screenshot or export action.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal