Back to skill

Security audit

Cn Countdown

Security checks for vulnerabilities and agentic risk

Overview

This is a local Chinese countdown/anniversary helper that stores user-entered dates in one disclosed local JSON file and does not show network, credential, or hidden execution behavior.

Before installing, expect a local CLI tool that saves event names, dates, tags, and notes in ~/.qclaw/workspace/countdown.json. Avoid storing highly sensitive personal details there, and treat the external website links at the end of the documentation as publisher promotion rather than part of the countdown feature.

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
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill describes functionality that reads and writes a local JSON file, but it does not declare any explicit tool scope or permissions. Undeclared file access weakens reviewability and least-privilege guarantees, making it harder for users or a host platform to understand what the skill can access or modify.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill name and primary description explicitly position the tool as Chinese-language only (e.g. '倒计时工具' and '中文倒数日/纪念日计算器') without indicating that users may choose another language or locale. Per the policy, a locale or language constraint should either be optional or clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest-style description presents the skill as a local countdown/anniversary calculator, emphasizing '纯本地,无账户,无云端'. However, the document ends with branding, a homepage URL, and a promotional call-to-action link to an external site unrelated to countdown functionality. This is a semantic mismatch between the stated narrow utility and the additional promotional behavior exposed in the skill file.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

A countdown/date calculator does not inherently require directing users to a vendor homepage or an AI-brand-diagnosis marketing page. Including these links introduces an unrelated promotional capability that is not necessary for recording dates or computing elapsed/remaining days.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The module docstring and CLI usage text are entirely in Chinese, and the skill name explicitly indicates a Chinese-only countdown tool. There is no natural-language indication that users can choose another language or that the locale restriction is required for a region-specific compliance or operational reason.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.