Security audit

AnyLink to Note

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: turns user-provided public links into notes, but users should avoid private or token-bearing URLs.

Use this for public links you are comfortable having fetched by third-party or local tooling. Do not use private documents, internal network URLs, localhost links, cloud metadata endpoints, or URLs containing access tokens unless you accept that those URLs and fetched contents may leave your local context.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger language is broad enough that ordinary phrases like '保存', '解析', '总结', or '收藏' alongside a link could invoke the skill unintentionally. Because the skill performs external fetching and content processing, accidental activation may send user-provided URLs to third-party services or retrieve remote content without clear user intent.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill sends supplied URLs to external services such as r.jina.ai and may also fetch remote content directly via curl or browser automation, but the user-facing description does not clearly disclose this data flow. This creates privacy and trust risks, especially if users share sensitive, private, or tokenized links believing the tool only processes them locally.

Static analysis

No suspicious patterns detected.