Back to skill

Security audit

Daily Finance Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed finance-news summary skill with optional Feishu scheduled delivery; the main issues are documentation clarity, not hidden or malicious behavior.

Install only if you want finance summaries and, if enabled, recurring Feishu messages. Review the Feishu destination before scheduling because pushed summaries may be visible to channel members or workspace administrators; expect minor documentation ambiguity around summary length and item count.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest describes the skill as '浓精简(3条精华)' and positions it as more refined than the base finance skill. However, the file later states that manual mode outputs a '完整版' full report and that scheduled push content contains 5-7 items, which materially exceeds the claimed concise 3-item scope.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill instructs users to configure scheduled delivery to Feishu without clearly warning that generated finance summaries and any associated account/channel metadata will be transmitted to an external messaging platform. This can cause unintentional disclosure of user preferences, scheduling patterns, or potentially sensitive business/market-monitoring information, especially in workplace contexts.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
71% confidence
Finding

文档直接给出 openclaw cron rm 删除定时任务的命令,但未对其效果做任何提示。虽然这是技能预期功能的一部分,仍建议在 markdown 中明确说明该操作会删除已有自动推送配置,避免用户误删。

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The push format section says daily pushes contain 5-7 highlights within 500 characters, while the '重要提示' section later says messages are controlled within 300 characters. These statements describe conflicting intended behavior for the same output mode.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.