ClawHub

FinXData

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed wrapper for querying FinXData financial APIs and does not show hidden persistence, destructive actions, or data exfiltration beyond the intended API calls.

Install this if you intend the agent to call FinXData for finance data. Configure FINXDATA_API_KEY only in trusted environments, keep FINXDATA_BASE_URL on the official trusted service unless you deliberately use another endpoint, and be aware that implicit invocation may use API quota for matching finance-data requests.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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
94% confidence
Finding
The skill instructs use of environment variables, shell commands, and outbound network access to a third-party API, but it declares no permissions or trust boundaries. This creates a real security governance gap: an agent or reviewer may not understand that the skill can access secrets and make authenticated external requests, increasing the risk of unintended data disclosure or misuse of the API key.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill enables implicit invocation without any trigger constraints, so the agent may call this finance-data skill automatically whenever a conversation loosely matches stocks, markets, macroeconomics, quotas, or API troubleshooting. That broad auto-routing can cause unintended external requests, disclosure of user prompts to a third-party API surface, or unexpected use of API quota/cost, especially in mixed-context conversations where the user did not explicitly request FinXData.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal