ClawHub
Back to skill

Security audit

QGIS Geospatial

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward QGIS helper that runs disclosed, user-directed geospatial processing commands on local files.

Install this only if you expect the agent to run QGIS processing on local map/geospatial files. Review requested input and output paths before approving runs, especially for batch jobs or operations that could overwrite or transform important datasets.

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
  • 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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The default prompt is broadly phrased ('Use $qgis to inspect QGIS algorithms and run a reproducible geospatial processing workflow on local files') and, combined with implicit invocation, can cause the skill to be triggered in situations without tight user intent validation. Because this skill executes geospatial processing on local files, an overly permissive trigger increases the chance of unintended file access or execution of sensitive local data workflows.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The description explicitly includes Chinese-only trigger wording ("中文触发：...") but does not state that language selection is optional or user-driven. This can be read as a locale/language policy constraint embedded in the skill metadata rather than an offered choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.