ClawHub
Back to skill

Security audit

Geo Local Optimizer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local marketing workflow guide with broad triggering language but no hidden execution, persistence, credential access, or destructive behavior.

Installers should know this skill may be invoked broadly for local-business marketing questions. It is best used when the user actually wants local discovery, map/listing, review, or AI-search optimization advice; otherwise ask for clarification before applying its full workflow.

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
93% confidence
Finding

The skill metadata defines a very broad trigger surface around local businesses, maps, reviews, service areas, and even implicit GEO intent. That can cause unnecessary or premature invocation in loosely related conversations, increasing the chance the agent shifts into a prescriptive optimization workflow when the user did not request it, which can degrade least-privilege behavior and introduce irrelevant data collection or task expansion.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The invocation guidance repeatedly uses expansive language like 'whenever' and 'strongly considered' while explicitly telling the system not to limit triggering to explicit local SEO wording. In practice, this biases the agent toward over-invocation and scope creep, which is dangerous in orchestration systems because the skill may be selected for conversations that only tangentially involve geography or local businesses.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.