ClawHub
Back to skill

Security audit

article-collect

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple local article bookmark tool, with expected but privacy-relevant URL browsing and local history storage behavior.

Install only if you are comfortable with the agent opening URLs you provide and saving article URLs locally. Avoid giving it private, internal, or sensitive URLs, and confirm which saved item is targeted before asking it to delete by number.

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 (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill defines broad natural-language triggers for listing saved articles, which can cause the agent to invoke the listing action on ambiguous user requests. That can expose a user's stored URLs or article history without sufficiently clear intent, creating a privacy and data-minimization problem.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documented delete_article flow allows deletion by index with no confirmation, warning, or preview of the item being removed. This makes accidental or manipulated destructive actions much more likely, especially if an agent misinterprets a request or if list ordering changes.

Missing User Warnings

Medium
Confidence
83% confidence
Finding
The skill performs a network fetch on a user-supplied URL with no validation, warning, or restriction. In an agent/runtime context, this can be abused for server-side request forgery-like access to internal services or sensitive local network endpoints, and it also transmits data to third parties without clear user disclosure.

Static analysis

No suspicious patterns detected.