ClawHub
Back to skill

Security audit

Finance Web Monitor

Security checks for vulnerabilities and agentic risk

Overview

This skill monitors public finance websites and schedules briefings in a way that is mostly disclosed and aligned with its stated purpose, with some persistence users should understand before using.

Before installing, be aware that scheduled monitoring can persist through cron and that the skill may keep a small local snapshot for change detection. Use it with public finance URLs you approve, confirm the schedule and cadence, and remove cron jobs or stored state when you no longer want monitoring.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill directs the agent to save rolling snapshots to a local workspace path without telling the user that fetched website content will be stored persistently. Even if the source sites are public, persistent local storage can create privacy, retention, and cross-run data exposure risks, especially if sensitive user-selected URLs or extracted content accumulate over time.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The scheduling instructions tell the agent to create recurring cron jobs but do not require an explicit warning that this creates persistent automated execution. Persistent tasks can continue making network requests and generating outputs after the immediate session, surprising users and creating operational or abuse risk if schedules are created too broadly or without clear limits.

Context-Inappropriate Capability

Medium
Confidence
90% confidence
Finding
The skill instructs the agent to update `references/sources.md`, which expands behavior from monitoring external finance websites into modifying repository content. That creates an unnecessary write capability and can let untrusted user-provided URLs or operational state influence tracked files, increasing the risk of unintended persistence or tampering in the skill repository.

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The markdown content is entirely in Chinese and provides no indication that users can choose another language or locale. Under the policy, forcing a specific language without opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.

External Transmission

Medium
Category
Data Exfiltration
Content
## 市场概览
- A股整体行情（指数+成交量）: https://quote.eastmoney.com/zs/000001.html
- 北向资金实时净流入: https://data.eastmoney.com/bkds/hgt.html
- 沪深300/权重走势: https://quote.eastmoney.com/zs/000300.html
- 港股整体行情: https://quote.eastmoney.com/hk/
- 南向资金实时数据: https://data.eastmoney.com/bkds/ngt.html
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
## 市场概览
- A股整体行情（指数+成交量）: https://quote.eastmoney.com/zs/000001.html
- 北向资金实时净流入: https://data.eastmoney.com/bkds/hgt.html
- 沪深300/权重走势: https://quote.eastmoney.com/zs/000300.html
- 港股整体行情: https://quote.eastmoney.com/hk/
- 南向资金实时数据: https://data.eastmoney.com/bkds/ngt.html
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Natural-Language Policy Violations

Low
Confidence
92% confidence
Finding
The instruction 'Emphasize risk controls for稳健偏好' introduces a Chinese-language phrase in the workflow without stating that language selection is optional or user-driven. This can impose a locale/language assumption instead of offering the user a choice.

Static analysis

No suspicious patterns detected.