ClawHub
Back to skill

Security audit

Versatile Map Maker

Security checks for vulnerabilities and agentic risk

Overview

This skill’s map downloads, local file processing, and SVG generation are disclosed and aligned with its map-making purpose.

Before installing, expect the agent to download public map data, use pip/npm when needed, and read/write local map files in a scratch area. Use care with proprietary or sensitive geodata, and review generated outputs for source accuracy and precision limits.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill instructs use of shell commands, package installation, filesystem reads/writes, and network fetching, but it does not declare permissions or otherwise constrain those capabilities. In an agent environment, undeclared powerful capabilities increase the risk of unintended command execution, data exfiltration, or modification of local files if the skill is invoked on untrusted inputs or in an over-privileged runtime.

Vague Triggers

Medium
Confidence
74% confidence
Finding
The description is broad enough to match many generic 'make a map' or visualization requests, which can cause the agent to invoke a skill that performs network access, shell execution, and file operations more often than necessary. That expands the attack surface by routing loosely related prompts into a high-capability workflow, especially when users provide external files or data sources.

Static analysis

No suspicious patterns detected.