Back to skill

Security audit

Ebook

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local ebook library tracker whose file writes, deletes, and exports match its stated purpose, with some usability cautions around deletion and overwrite behavior.

Install this if you want a local command-line ebook tracker. Be aware that it writes reading history and notes to ~/.ebook/data.jsonl, delete removes a book and related records, and export can overwrite the path you provide.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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 (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill advertises and relies on local file read/write capabilities (~/.ebook/data.jsonl and export output paths) but does not declare any explicit tool scope or permission boundaries. That makes the effective access surface ambiguous and can allow an agent/runtime to grant broader filesystem access than users would reasonably expect from the metadata alone.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The delete command removes a book and all related sessions, highlights, and reviews, then immediately overwrites the backing data file. Although the command name suggests deletion, there is no confirmation prompt or inline warning comment/user-facing disclosure near the irreversible cascade delete behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest description says to use the skill when 'cataloging books, logging reading sessions, or organizing digital libraries' without defining narrower trigger phrases or exclusion conditions. In a manifest file, this kind of broad natural-language invocation guidance can match many ordinary user requests and may cause unintended activation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The export command serializes library, highlight, or review data to a user-specified output path, which can overwrite files via write mode. While export is part of the tool's purpose, the code provides no user-facing warning or confirmation when writing potentially sensitive reading history and notes to disk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.