ClawHub
Back to skill

Security audit

Pixelvault List

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to do what it says: help users retrieve PixelVault-hosted image URLs and related upload details, with no evidence of malware or hidden behavior.

Install only if you are comfortable with the agent showing PixelVault CDN links and, when detailed output is requested, upload metadata such as filenames, MIME types, sizes, folders, and timestamps in the conversation.

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)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger description uses broad natural-language phrases such as 'find that image URL' and 'what images have I hosted,' which can cause the skill to activate in situations where the user did not clearly intend to enumerate hosted assets. Because the skill returns CDN URLs and, optionally, full metadata for prior uploads, unintended invocation can expose sensitive links or file details to the conversation unnecessarily.

Missing User Warnings

Low
Confidence
90% confidence
Finding
The skill documentation does not warn that listing uploads may reveal direct CDN URLs and, with '--json', additional metadata like filenames, folder names, MIME types, sizes, and timestamps. In a conversational agent setting, lack of a warning increases the chance that users will invoke the skill without understanding that previously uploaded asset details will be surfaced back into chat.

Static analysis

No suspicious patterns detected.