Back to skill

Security audit

Cn Date Validator

Security checks for vulnerabilities and agentic risk

Overview

This is a small local date-validation utility with minor documentation and presentation issues but no evidence of hidden, persistent, privileged, or malicious behavior.

Reasonable to install if you want a simple local date validator. Be aware that it contains Chinese promotional links and accepts more input formats than documented, so check ambiguous slash-form dates carefully.

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
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The markdown is primarily in English, but the promotional footer switches to Chinese-language phrasing such as "免费检测你的品牌在AI搜索中有没有存在感" without user opt-in or explanation. This can violate a language/locale policy that requires respecting the user's language preference unless a region-specific constraint is documented.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest says the skill supports YYYY-MM-DD, YYYY/MM/DD, and DD-MM-YYYY, but the code also accepts DD/MM/YYYY and MM/DD/YYYY. This is a semantic mismatch between the claimed supported scope and the actual behavior, even though the extra behavior is not inherently dangerous.

Content

No source excerpt is available for this finding.