ClawHub
Back to skill

Security audit

opd-data

Security checks across malware telemetry and agentic risk

Overview

This is a scoped OPD financial data query skill with disclosed API-key handling and optional chart rendering; I found no hidden exfiltration, destructive behavior, or deceptive instructions.

Install this if you are comfortable giving the skill access to an OPD API key and sending your chosen query parameters to api.originp.com. Use the interactive --set-key flow rather than pasting the key into chat, and review or skip the optional echarts-ai-skill chart workflow if you do not want generated local HTML opened in a browser.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding
The skill declares no formal permissions, yet the documentation clearly describes capabilities to read environment variables, write a credential file, and make outbound network requests. This mismatch weakens sandboxing and auditability because operators may trust the manifest while the skill still handles secrets and external I/O.

Context-Inappropriate Capability

Medium
Confidence
89% confidence
Finding
The skill instructs users/agents to invoke a separate Node.js chart tool and open generated HTML in a browser, which expands execution and rendering scope beyond simple financial-data querying. That creates an additional trust boundary: untrusted API-derived content could flow into chart generation and local browser rendering, increasing risk of script injection, unsafe local file handling, or abuse through the downstream tool.

Intent-Code Divergence

Medium
Confidence
93% confidence
Finding
The documentation claims the skill's external behavior is limited to OPD API access, but later directs execution of external Node.js tooling and opening a browser. This contradictory disclosure can mislead reviewers and users about the true attack surface, causing them to underestimate secondary execution paths and data egress/rendering risks.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.