Back to skill

Security audit

Stock Top Gainers

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently fetches public China A-share top-gainer data and does not show hidden persistence, credential access, destructive behavior, or unrelated data handling.

Before installing, understand that the skill browses third-party financial websites to obtain public market data and may fall back to bundled cached sample data if live browsing fails. Treat outputs as informational only, especially because market data can be delayed or stale.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (12)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The README explains how to use the skill and provides a generic query phrase, but it does not define explicit activation boundaries, exclusions, or negative examples. In a markdown skill description, this lack of trigger specificity can cause unintended invocation for loosely related requests about stock gainers or rankings.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are broad enough to match many ordinary stock-market queries, which can cause the skill to activate more often than intended. Over-broad activation increases the chance of unintended browsing to third-party financial sites and could override a more appropriate, lower-risk response path.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 31)May include surrounding context.

md
- URL: `https://www.iwencai.com/unifiedwap/result?w=近 10 日涨幅排名`

**备用**:东方财富网(网络不稳定时)
- URL: `https://data.eastmoney.com/rzrq/`
- 导航至「区间统计」→「10 日涨幅」排行

## 操作步骤

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/fetch_gainers.py (reported line 43)May include surrounding context.

python
print(f"  🌐 访问同花顺问财:{url}")
        
        # 使用 browser 工具打开页面
        browser_result = subprocess.run(
            ["openclaw", "browser", "open", "--url", url],
            capture_output=True, text=True, timeout=30
        )

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/fetch_gainers.py (reported line 53)May include surrounding context.

python
return None
        
        # 等待页面加载
        subprocess.run(["sleep", "3"], capture_output=True)
        
        # 获取 snapshot
        print(f"  📸 获取页面 snapshot...")

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/fetch_gainers.py (reported line 57)May include surrounding context.

python
# 获取 snapshot
        print(f"  📸 获取页面 snapshot...")
        snapshot_result = subprocess.run(
            ["openclaw", "browser", "snapshot", "--refs", "aria"],
            capture_output=True, text=True, timeout=30
        )

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file’s natural-language documentation is entirely in Chinese, including the top-level description and function docstrings, with no indication that this language choice is optional or required for a region-specific workflow. Under the policy rule, forcing a specific language without user opt-in is a natural-language locale violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The description is written only in Chinese and specifically targets A-share stocks, which implies a fixed locale/language context without stating that this is region-specific or optional. The policy allows locale constraints when clearly documented and justified, but this file does not explicitly say the skill is intended only for Chinese-market users.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This JSON file encodes all field names in Chinese (for example, 排名, 股票代码, 股票简称) and provides no indication that the locale is optional or intentionally region-scoped. Under the policy rule for natural-language violations, a fixed language/locale can be a concern when no user opt-in or justification is present.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The natural-language metadata in the description and keywords is entirely in Chinese and specifically references A-share stocks, but the file does not state that the skill is region-specific or offer any language/locale opt-in. Under the policy, forcing a specific language or locale without user choice or clear justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The file’s natural-language instructions and stated behavior are entirely Chinese-specific, including the target query text and surrounding documentation, without indicating that language/locale is optional or limited to a justified region-specific use case. Under the policy, forcing a specific language or locale without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.