ClawHub
Back to skill

Security audit

yance-report-gen

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward teaching-oriented investment report generator that reads user-supplied JSON files and writes a markdown report.

Before installing, understand that this skill will read the JSON report files you provide and create a markdown report in the output directory you choose. Use a dedicated output folder if you want to avoid writing into an unintended location; the artifact showed no network calls, credential handling, or hidden background behavior.

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
82% confidence
Finding
The skill documents execution of a local Python script that reads multiple input JSON files and writes a generated report to an output directory, but the skill metadata declares no permissions. This creates a capability/permission mismatch that can mislead reviewers or enforcement systems, and in practice enables filesystem access broader than the declared trust model suggests.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.