ClawHub
Back to skill

Security audit

EPUB Read

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a local EPUB parsing and reading helper that saves extracted book content and reading progress on disk as part of its stated purpose.

Install dependencies in a virtual environment, parse only EPUBs you are allowed to process, keep the output directory private, delete generated artifacts when no longer needed, and only run the integration test with its default temporary path or a dedicated disposable directory.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 instructs the agent to run local Python scripts, read parsed book outputs, and update session state, which implies file read/write and shell execution capabilities, yet no permissions are declared in the metadata. This creates an auditability and least-privilege gap: operators and users cannot accurately assess what the skill is allowed to do, and an agent runtime may grant broader access than expected.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The README explicitly documents that parsed book contents, metadata, chunk files, and session state are written to disk, but it does not clearly warn users about the persistence and sensitivity implications of doing so. This can lead users to unintentionally store copyrighted, sensitive, or private ebook content and reading history on shared or insecure systems.

Static analysis

No suspicious patterns detected.