Back to skill

Security audit

Anime Ebook Reader

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language anime and light-novel ebook helper with disclosed reading and progress features and no executable code.

Before installing, users should understand that the assistant may keep track of book titles and reading progress during the conversation. Avoid uploading ebooks or reading lists that reveal sensitive interests unless you are comfortable sharing them with the agent session.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The rule '中文优先' directs the skill to prioritize Chinese by default. This is a language-policy constraint expressed in natural language, and the file does not indicate that users can choose another language or explicitly opt into Chinese-first behavior.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill states it will remember the user's reading position but provides no disclosure about whether that state is stored only in-session, persisted across sessions, or shared with other components. This creates a privacy and transparency gap that can expose behavioral data such as reading habits or interests, even if the stored data seems low sensitivity.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

Recording reading lists and progress without an explicit privacy notice means the skill may collect preference and activity data without informed user awareness. Even for an ebook reader, this can reveal interests, habits, or sensitive topics a user reads about, making the issue a real but low-severity privacy weakness.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file contains user-facing natural language exclusively in Chinese, including headings, platform descriptions, and reading guidance. Under the policy rule for language or locale constraints, forcing a specific language without user opt-in or justification can be a policy violation.

Content

No source excerpt is available for this finding.