ClawHub
Back to skill

Security audit

每日英语诗歌推送

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly describes a scheduled daily poetry fetch and Feishu push, with no hidden code, credential access, destructive behavior, or unrelated authority found.

Before installing, confirm that an automatic daily Feishu post is appropriate for the target chat or workspace, and consider copyright/source-quality expectations because the skill forwards full poem text and analysis from third-party sites.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill is designed to fetch content from multiple external websites and automatically forward the retrieved material to Feishu, but it does not disclose that network access and outbound delivery will occur. This creates a real transparency and data-handling risk: externally sourced content could be inaccurate, maliciously manipulated, copyrighted, or unexpectedly include tracking or unsafe text, and users are not warned that such content will be redistributed automatically.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction '英文内容' requires the push content to be in English, imposing a language constraint. The file does not indicate that users can choose the language or that the English-only requirement is an explicitly justified locale-specific constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.