ClawHub
Back to skill

Security audit

BookStack

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward BookStack API skill that uses user-provided credentials to manage wiki content as advertised.

Install this only for BookStack instances you want an agent to access. Use a least-privilege API token, protect the token like a password, and review update or delete commands carefully before running them against important documentation.

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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill declares required environment variables and clearly depends on outbound API access, but it does not declare explicit permissions for those capabilities. This creates a transparency and policy-enforcement gap: users or orchestration systems may not realize the skill can access secrets and make network requests to a remote BookStack instance.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The documentation promotes create, update, and delete operations against a live knowledge base without prominent safety guidance, confirmation requirements, or warnings about destructive effects. In an automation context, this can lead to accidental overwrites, deletions, or bulk content corruption when the skill is invoked with the wrong target IDs or generated content.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.