ClawHub
Back to skill

Security audit

Anime Ebook Reader

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only ebook reading helper that handles user-provided books and reading progress without installing code or requesting sensitive access.

Install this if you want help reading and summarizing uploaded light novels or ebooks. Avoid uploading sensitive or copyrighted material unless you are comfortable with how your agent platform handles files, and tell the assistant when you want the original language preserved instead of Chinese-preferred output.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill description and trigger scenarios are broad enough to activate on general ebook, note-taking, or recommendation requests without clear boundaries. Overbroad routing can cause the wrong skill to handle unrelated user content, increasing the chance of unnecessary file access, unintended persistence of reading data, or processing of sensitive uploaded documents.

Natural-Language Policy Violations

Medium
Confidence
80% confidence
Finding
Forcing Chinese as the default language without user opt-in can override user preference and cause the assistant to transform or summarize content in an unexpected language. In a reading skill, this may lead to misinterpretation, degraded accessibility, and accidental disclosure if translated excerpts are shown in contexts where the user expected the original language.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.