ClawHub
Back to skill

Security audit

Book Skill Generator

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed book-methodology-to-skill generator, with expected file reading and artifact generation behavior that users should review before installing generated skills.

Install only if you want an agent to process book titles or uploaded book files and generate new skills. Review each generated SKILL.md before installing it, especially when the source is a private document or web-derived content.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger description includes broad phrasing like “或类似需求,” which makes activation boundaries ambiguous and can cause the skill to run for loosely related requests. In this skill, over-triggering is meaningful because it can lead the agent to read uploaded files, perform web searches, and generate packaged artifacts when the user did not explicitly request that workflow.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The README recommends invoking the skill with a natural-language phrase like “从《精益创业》提取方法论，生成对应的 skill,” which is broad and conversational rather than a narrowly scoped command. Overly broad triggers can cause accidental activation in unrelated conversations about books or methodology extraction, leading the agent to generate or install skills unexpectedly; in a skill generator context, that increases the chance of unintended file creation or execution of downstream generation workflows.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.