ClawHub
Back to skill

Security audit

Ppshu Github

Security checks across malware telemetry and agentic risk

Overview

This skill is a local HTML visualization helper whose file creation and diff-report behavior are disclosed and aligned with its purpose.

Before installing, be comfortable with the agent creating local HTML/JavaScript files in your project and reading files you ask it to compare. Prefer the default .ppshu output folder, review generated reports before sharing because they may embed source text, and avoid overriding PPSHU_DIR or --dir to sensitive locations unless intentional.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill instructs the agent to read/write files, invoke Python scripts, use shell commands, reference environment variables, and present generated HTML, but it declares no permissions. This mismatch weakens security review and user consent because the operational capabilities are broader than what the manifest communicates, and the HTML-generation workflow could be abused to write arbitrary files or create active content in the project context.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.obfuscated_code

Potential obfuscated payload detected.

Warn
Code
suspicious.obfuscated_code
Location
assets/mermaid.min.js:371