ClawHub
Back to skill

Security audit

10jqka Concept

Security checks for vulnerabilities and agentic risk

Overview

This stock concept lookup skill performs expected public web scraping and small local caching, with disclosure gaps but no evidence of harmful behavior.

Before installing, understand that running the scripts will contact Tonghuashun/iWencai-related sites and may keep queried stock results in a local OpenClaw cache for about 24 hours. Avoid it for private trading research if query privacy matters, or remove/disable the cache path before use.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding
The skill embeds executable examples and operational guidance that use network access and potentially local file capabilities, but it does not declare any permissions or capability boundaries. This creates a transparency and governance problem: users and hosting platforms cannot accurately assess what the skill may access, increasing the risk of unintended data access or unsafe execution in environments that rely on declared permissions.

Tp4

High
Category
MCP Tool Poisoning
Confidence
89% confidence
Finding
A mismatch between the declared purpose and the actual or documented behavior is a real security concern because it prevents informed consent and can hide broader data collection or automation than users expect. If the skill can batch process stocks, access additional domains, use local caches, or return preloaded mappings beyond the stated F10 scraping behavior, it expands both attack surface and trust risk in ways the description does not disclose.

Static analysis

No suspicious patterns detected.