ClawHub
Back to skill

Security audit

GeoJSON

Security checks for vulnerabilities and agentic risk

Overview

This GeoJSON skill appears to be a read-only helper for inspecting and validating GeoJSON files or inline payloads, with no evidence of hidden network access, persistence, or destructive behavior.

Install this if you want a lightweight GeoJSON inspection helper. Review file paths before asking it to inspect data, since it can read the file path you provide, and use a dedicated GIS tool for transformations, reprojection, clipping, or editing.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding

The skill invokes a local Python script against user-supplied file paths and inline JSON, which implies file-read capability, but it does not declare any explicit tool scope or allowed-tools boundary. In a skill system, missing scope declarations can let the runtime grant broader-than-intended access or make reviewers unable to verify least-privilege constraints, increasing the chance of unintended file access if the skill is triggered on attacker-controlled input.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The invocation guidance mixes specific terms with broader phrasing like asking "about GeoJSON" or "GeoJSON debugging," which could cause the skill to activate for general discussion rather than only for inspection/validation tasks. The file does not provide negative examples or tighter boundaries for when the skill should not activate beyond later usage guidance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.