ClawHub
Back to skill

Security audit

Sunset Bot (国内火烧云预报)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrowly scoped sunset forecast notifier that uses a weather API, optional Feishu notifications, and local logs in ways that match its stated purpose.

Install this if you want a China-focused sunsetbot.top forecast monitor and are comfortable configuring a Feishu Open ID for notifications. Review any cron setup before enabling it, since that will run recurring forecast checks and append local weather logs.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description and operational instructions are written as a China-specific domestic version and direct use when users ask about fire-cloud forecasts or scheduled notifications, but they do not offer any user language or locale choice. This creates a natural-language locale constraint that is not presented as an opt-in or explicitly justified as a region-limited compliance requirement.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill instructs use of a personal Feishu Open ID from config without clearly warning the user that this identifier will be used by the messaging tool and may be exposed in tool invocations, logs, or downstream integrations. In a notification skill, this is a real privacy concern, though limited in scope because the identifier is intended for notification routing rather than broad authentication.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The example config uses Feishu-specific fields and Chinese-language placeholder text, which implies the skill is oriented to a specific language/platform without any visible opt-in or alternative locale choice. This can conflict with language/locale policy requirements when the skill is expected to be generally applicable.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.