ClawHub
Back to skill

Security audit

Read It Later

Security checks for vulnerabilities and agentic risk

Overview

This read-it-later skill is a simple markdown-based link and note saver, with a disclosed but privacy-relevant behavior of fetching saved URLs for tagging.

Install this if you want a lightweight markdown reading list. Be aware that when you save a link, the skill may fetch that page to summarize or tag it, so do not use it with confidential, localhost, intranet, or token-bearing URLs unless you are comfortable with that request being made.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to automatically fetch arbitrary user-provided URLs with `kimi_fetch` without warning the user that network access will occur or discussing privacy implications. This can expose sensitive URLs, trigger requests to internal or private endpoints, or surprise users who expected only local markdown storage behavior.

Static analysis

No suspicious patterns detected.