ClawHub
Back to skill

Security audit

Check Workday CN

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed utility for checking China workdays using a hardcoded public holiday JSON source.

Before installing, understand that the skill depends on a public jsDelivr-hosted holiday dataset using a mutable branch reference, so incorrect or changed upstream data could affect the answer. It does not appear to read private files, use credentials, persist changes, or execute remote payloads.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill instructs the agent to fetch holiday data from an external CDN but does not declare any tool scope or permissions boundary for that network access. This creates an undeclared capability: an agent or runtime may perform outbound requests without explicit review, increasing supply-chain and data exfiltration risk if the remote source is compromised or the skill is modified later to query additional endpoints.

Static analysis

No suspicious patterns detected.