ClawHub
Back to skill

Security audit

Equal Data - China A Share Stock Data Service Skill

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed financial data lookup skill that uses an API key and third-party service, with some privacy and trigger-scope caveats but no evidence of hidden or destructive behavior.

Install only if you intend to use Equal Data as a third-party financial data provider. Treat the API key like a credential, prefer environment-variable storage over committing it anywhere, and avoid putting confidential portfolio, client, or proprietary trading context into prompts that may be turned into API queries.

SkillSpector

By NVIDIA
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
93% confidence
Finding
The description is ambiguous about when the skill should be invoked and how aliases, abbreviations, or seat names should be matched for `hotMoneyName`. In an agent setting, unclear invocation boundaries can cause the model to call the financial data interface on weak or unintended user signals, producing incorrect entity resolution, privacy-sensitive inferences, or unreliable downstream analysis.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger list is extremely broad and includes common finance-related keywords such as 新闻, 公告, 股票, 基金, and 热门榜单. In an agent framework, overly generic triggers can cause the skill to activate unintentionally, sending user prompts or contextual data to the external provider when the user did not intend to invoke this integration. Because this skill depends on a third-party API, accidental invocation increases privacy and data-handling risk.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill requires an API key and demonstrates calls to a third-party service, but it does not clearly warn users that their queries and supplied parameters may be transmitted to an external provider. This can create a transparency and privacy problem, especially if users include sensitive portfolio, research, or proprietary trading context in prompts that get forwarded. In a financial-data context, external sharing of query content may be operationally sensitive even if no direct trading occurs.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.