ClawHub
Back to skill

Security audit

Querit API

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Querit.ai API integration guide with disclosed API-key and network use, but users should avoid sending sensitive queries or private URLs to the external service.

Install only if you intend to use Querit.ai. Keep QUERIT_API_KEY in an environment variable or secret manager, do not paste or commit it, and avoid sending confidential prompts, customer data, private URLs, localhost/internal-network URLs, or regulated content unless your organization has approved that use.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill explicitly requires an API key from the environment and instructs use of external HTTP endpoints, but it does not declare corresponding permissions/capabilities in a formal permission model. That mismatch can bypass operator expectations or platform policy checks, increasing the chance that network access and secret use occur without clear review.

Missing User Warnings

Medium
Confidence
83% confidence
Finding
The documentation encourages crawling arbitrary URLs and returning page content/metadata, but it does not warn about privacy, authorization, internal-network targeting, or handling of sensitive retrieved data. In an agent or RAG context, this can normalize unsafe use of user-supplied URLs and increase risk of SSRF-style access attempts, ingestion of private content, or downstream exposure of sensitive page data.

Missing User Warnings

Low
Confidence
90% confidence
Finding
This documentation describes sending user-supplied search queries and filters to a third-party API but does not explicitly warn that potentially sensitive input will leave the local system. In a search/RAG integration skill, users may unknowingly forward confidential prompts, internal URLs, or regulated data to an external provider, creating a privacy and compliance risk even though this is not an implementation bug.

Static analysis

No suspicious patterns detected.