ClawHub
Back to skill

Security audit

IT之家 日榜/周榜/月榜 热门文章

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches public IT之家 ranking articles and can optionally send or schedule them to a user-selected messaging channel, which matches its stated purpose.

Before installing, verify that you want an agent to access ithome.com and, if using push or cron, explicitly choose the messaging channel, recipient/session, timezone, and recurrence. Disable or avoid the optional cron setup if you only need on-demand ranking retrieval.

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
  • 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 (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill instructs the agent to create and run Python code that makes outbound network requests to ithome.com, but the skill metadata does not declare any explicit tool scope such as allowed tools or permissions. This creates a policy and containment gap: an agent may perform network-capable actions without transparent declaration or review, making misuse or unexpected data flows harder to detect and govern.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill includes commands to send fetched content to external messaging channels and to set up recurring scheduled pushes, but it does not prominently warn that this causes automatic outbound transmission to third-party destinations. That omission can lead users to enable persistent exfiltration-like behavior or unintended notifications without understanding that content will be transmitted automatically and repeatedly.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The script's natural-language strings and interface values are entirely fixed in Chinese, including the docstring, default rank labels, and output text, with no indication that users may choose another language. This can violate a language/locale policy when a skill forces a specific language without opt-in or documented justification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This code performs an HTTP request to an external site, which transmits system metadata such as the User-Agent and the user's network identity, but the operation has no visible user-facing warning, log message, or inline disclosure beyond a brief docstring. For a code file, this qualifies as a network operation without clear disclosure.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.