ClawHub

SQLBot

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed SQLBot helper that uses a user-provided API key to query, switch context, ask questions, and export dashboards, with no evidence of hidden or malicious behavior.

Install this only if you intend to let the agent use a SQLBot API key for the reachable SQLBot instance. Use a least-privilege key, verify SQLBOT_BASE_URL before use, avoid placing secrets in shared skill directories, review workspace switches before running them, and choose dashboard export paths that will not overwrite important files.

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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill performs networked API operations, reads configuration from a .env file, and can write exported dashboard files, but it does not declare any permissions or equivalent trust boundaries in the skill metadata. This creates a transparency and consent problem: a caller may invoke the skill without realizing it can access secrets, contact external services, and write to disk, which increases the risk of unintended data exposure or unsafe file writes.

Missing User Warnings

Low
Confidence
89% confidence
Finding
The dashboard export path is fully user-controlled and is written to after automatically creating parent directories, with no restriction to a safe workspace directory. In agentic or automated contexts, this can overwrite arbitrary files accessible to the process, enabling data loss, tampering with user configuration, or placement of files in sensitive locations.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal