ClawHub
Back to skill

Security audit

markdown-bundle-browser

Security checks across malware telemetry and agentic risk

Overview

This skill transparently bundles user-selected Markdown files into an offline HTML viewer, with no evidence of hidden network access, credential use, persistence, or destructive behavior.

Use this skill on directories you intend to package, and remember that the generated HTML contains the full text of the bundled Markdown files. Avoid bundling private notes, secrets, or untrusted Markdown unless you are comfortable opening and sharing the resulting HTML.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill instructs the agent to run a Python bundling script that recursively reads Markdown files and writes a generated HTML file, but the skill metadata declares no permissions. This creates a permission/behavior mismatch that can bypass user expectations and platform safeguards, especially because the skill operates over arbitrary directories and output paths.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger conditions are broad enough to activate on common documentation-related requests such as 'view all documents' or when there are 3+ Markdown files. Overbroad triggering can cause the agent to invoke file-reading and file-writing behavior in situations where the user did not explicitly ask for bundling, increasing the chance of unnecessary data exposure or unintended artifact generation.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.