ClawHub
Back to skill

Security audit

stock-rumors-zh

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed AISA-based market-rumor scanner that uses an API key and external service as expected, with no evidence of trading actions, persistence, local credential access, or destructive behavior.

Install only if you trust AISA and the configured API endpoint. Use a dedicated AISA API key where possible, avoid sending private trading strategies or personal financial details, leave AISA_BASE_URL unset unless you intentionally trust another endpoint, and treat the output as unverified information rather than financial advice.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger description is broad enough that normal discussions of market news, rumors, analyst opinions, or early signals could activate this skill unintentionally. Over-broad activation can cause unnecessary external data access and route user queries to a tool that handles sensitive market-related topics without sufficient user intent confirmation.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The 'when to use' section repeats broad activation criteria and provides only limited exclusion cases, leaving the invocation boundary unclear. In an agent setting, unclear boundaries increase the risk of misrouting ordinary finance questions into a speculative rumor-scanning workflow and unnecessarily sharing prompts or tickers with an external service.

Static analysis

No suspicious patterns detected.