ClawHub
Back to skill

Security audit

drillr — Power Terminal for Deep Financial Research

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed read-only financial research client that sends the user's question to a single external API and prints the response.

Install only if you are comfortable sending financial research prompts to the drillr external API. Do not include secrets, credentials, account-specific data, or nonpublic business information, and verify investment-relevant facts against primary sources before relying on the output.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill declares no permissions, but its documented invocation runs Python and makes an outbound HTTPS request to a third-party endpoint. This mismatch is a real security issue because the host/user may rely on the manifest to understand or enforce capabilities, and undeclared network and shell execution expand the trust boundary to remote content and local code execution.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.