ClawHub
Back to skill

Security audit

Kindle知识卡片生成器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward knowledge-card generator that writes a local HTML file and previews it, with no evidence of hidden data access or malicious behavior.

Install only if you want an agent to create local HTML knowledge cards. Be aware it may overwrite an index.html in the current working directory, open a browser preview, and load Tailwind/Google Fonts from external CDNs; avoid feeding highly sensitive text unless those side effects are acceptable.

SkillSpector

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 (4)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger phrases are broad and include common language such as '知识卡片' and similar generic generation terms, which can cause the skill to activate during ordinary user requests that were not meant to invoke this specific capability. In an agent setting, ambiguous activation boundaries increase the chance of unintended execution, confusing tool routing, and accidental processing of user content under the wrong skill.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The README states that saying a simple phrase will 'automatically generate' a card, which implies implicit activation without clearly defined consent or routing boundaries. This makes accidental invocation more likely and can cause the agent to perform actions when the user may only be discussing the concept rather than requesting this specific skill.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger list includes broad phrases such as generic 'knowledge card' variants and common Chinese wording that could match ordinary user requests unintentionally. This can cause the skill to activate when the user did not explicitly intend to invoke it, increasing the chance of unexpected file-generation behavior and reducing user control over tool use.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill directs the agent to write an `index.html` file and automatically open a browser preview without requiring explicit user confirmation. This creates an unsafe side effect boundary: a user asking for content transformation may unexpectedly trigger filesystem writes and browser execution of generated HTML, which is especially risky because the HTML incorporates user-provided content and loads Tailwind from a CDN.

Static analysis

No suspicious patterns detected.