ClawHub
Back to skill

Security audit

Markdown Images to R2

Security checks across malware telemetry and agentic risk

Overview

This skill is a coherent Markdown image publishing helper that discloses its file changes, credential use, and network upload behavior, with explicit confirmation gates before upload or rewrite actions.

Review the dry-run plan before using apply mode, keep R2 credentials in a secure environment rather than command-line history, and only run uploads for Markdown and image paths you intend to make public.

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
95% confidence
Finding
The skill describes capabilities that read files, write backups and modified Markdown, access environment variables for credentials, and perform network uploads, but it does not declare corresponding permissions. This creates a transparency and consent gap: an agent or reviewer may underestimate what the skill can access or do, increasing the risk of unintended file modification, credential exposure, or external data transfer during use.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.