ClawHub
Back to skill

Security audit

Aries Holiday Weekday

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly does what it says, but it includes an unrestricted URL-fetch helper and hardcoded government-search signing values that need review before installation.

Install only if you are comfortable with the skill making outbound web requests and writing yearly cache files. Before broader use, the publisher should restrict notice fetching to HTTPS gov.cn hosts, remove or clearly document the captured/static signing material, and declare network and cache permissions explicitly.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill instructs use of file reads/writes for caching and network access to query gov.cn, but no corresponding permissions are declared. This creates a capability/permission mismatch that can bypass user or platform expectations, increasing the risk of unintended data access, persistent local modification, or external communication if the runtime does not enforce least privilege strictly.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The script embeds authentication/signing material directly in source code and sends it in outbound headers, which exposes reusable secrets to anyone who can read the repository, package, logs, or built artifact. Even if these values are intended for a public integration, hard-coding them prevents rotation, encourages uncontrolled reuse, and can enable abuse of the upstream service or impersonation of this client.

Static analysis

No suspicious patterns detected.