ClawHub
Back to skill

Security audit

DataHub Unified Data Layer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documented financial data retrieval helper, with no bundled executable payload or hidden behavior found in the reviewed artifact.

Before installing, confirm you trust the separate DataHub code path you configure, because this skill relies on that external local implementation. Use provider credentials and cookies only when needed, and prefer explicit requests for financial data fetching to avoid unintended outbound queries.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger phrases in the metadata are very broad, including generic requests like '获取数据' and '查行情', which can cause the skill to activate in many ordinary finance-related conversations. This increases the chance the agent will invoke external data retrieval and credential-backed integrations without a sufficiently specific user intent boundary.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The description presents convenience and production readiness but does not clearly warn that the skill performs outbound requests to numerous third-party and official data sources and may use environment-configured credentials or cookies. Users and orchestrators may therefore invoke it without understanding that external network access and secret-backed API usage will occur.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The 'When to Activate' section uses expansive conditions like any need to get financial data, batch retrieval, natural-language financial queries, or pipeline construction. In context, this skill can reach many external sources and use configured API credentials, so overbroad activation materially raises the risk of unintended external requests and data disclosure through unnecessary skill invocation.

Static analysis

No suspicious patterns detected.