ClawHub
Back to skill

Security audit

Hugmap Tech News Graph

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only HugMap query helper that is clear about using Python and outbound HugMap API requests.

Install only if you are comfortable sending HugMap search terms and entity IDs over the network. Leave HUGMAP_BASE_URL at the default HugMap site unless you intentionally want to use another trusted endpoint.

SkillSpector

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
87% confidence
Finding
The skill documentation indicates code execution with network access and environment-variable input (`HUGMAP_BASE_URL`), but it does not declare corresponding permissions. This creates a transparency and policy-enforcement gap: operators may approve or run the skill without realizing it can make outbound requests to a configurable endpoint, which could enable unintended data egress or requests to untrusted infrastructure if the base URL is overridden.

Static analysis

No suspicious patterns detected.