ClawHub

Grok Image Generation

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward xAI image-generation helper that sends user prompts and selected images to xAI and saves returned files locally, with no hidden or destructive behavior found.

Install this only if you are comfortable using xAI's remote API. Do not provide private prompts or source images unless you are willing to send them to xAI, and keep the XAI_API_KEY protected. Review or clean the output directory if generated images, prompts, URLs, or response metadata should not be retained.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill directs the agent to use environment variables, read local files, write outputs, and make network calls, but it does not declare any permissions. This creates a governance and transparency gap: an orchestrator or reviewer cannot accurately assess or constrain what the skill is allowed to access, increasing the risk of unintended file access, secret use, or outbound data transfer. In this context, the capability set is expected for an image-generation wrapper, so the issue is not inherently malicious, but it is still a real security control failure.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The edit path sends user prompts and local image contents to a third-party API by converting local files to data URIs and posting them to xAI. In a local automation skill, this is expected functionality, but it is still a real privacy/security concern because potentially sensitive workspace images may be exfiltrated off-host without any explicit notice, confirmation, or scoping controls.

Missing User Warnings

Low
Confidence
87% confidence
Finding
The script automatically writes generated images and the full API response to disk, which may include prompt text, returned URLs, metadata, or other sensitive artifacts. This creates a local data exposure risk if the output directory is shared, synced, or later accessed by other users or processes, especially since there is no warning or retention control.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal