ClawHub
Back to skill

Security audit

qiyue-liuren-drawer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple disclosed integration that sends a user’s divination question and optional time to QiyueAstro’s public API and displays the returned chart summary.

Install only if you are comfortable sending the question text and optional casting time to qiyueastro.com. Avoid entering sensitive personal, medical, financial, or confidential business details, and expect outputs to include a QiyueAstro promotional link.

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 (2)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill sends user-provided `question` content and optionally a timestamp to an external public API, but the description does not clearly warn users before invocation that their inputs leave the local system. This creates a privacy and consent issue, especially because questions may contain sensitive personal, financial, or health-related details that users would not expect to be transmitted to a third party.

Natural-Language Policy Violations

Medium
Confidence
81% confidence
Finding
The formatting rules require a fixed output style and a mandatory Chinese promotional call-to-action, regardless of the user's preferred language or locale. While not a classic security flaw, this can override user intent, cause misleading UX, and pressure the agent into adding third-party promotional content the user did not request.

Static analysis

No suspicious patterns detected.