Back to skill

Security audit

Geo Local Search Optimization

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only local business promotion skill whose contact-detail collection is disclosed and purpose-aligned, though users should only provide information meant for public release.

Install only if you want help creating public local-business promotion content. Provide only contact details you are authorized to publish, avoid personal or residential information unless it is already intended for public business listings, and verify all generated claims before posting.

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
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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The README asks users to provide sensitive business-identifying and contact information, including exact address, phone number, and licensing details, but gives no guidance on minimization, storage, retention, sharing, or redaction. In an agent skill context, this can lead users to expose data unnecessarily to the tool, model provider, logs, or downstream systems without informed consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill explicitly requests and reproduces sensitive business contact data, including exact address and phone number, in generated content without any warning, consent check, minimization guidance, or handling restrictions. While this is framed as local-business promotion, the workflow encourages broad redistribution of identifiable contact details, which can create privacy, scraping, harassment, or doxxing risks if the data is personal, home-based, or submitted without proper authorization.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The README states the skill is optimized for Chinese local business search patterns, which is a locale-specific constraint. Because the file does not clearly present this as an explicit opt-in or narrowly justified regional limitation in the activation/instruction context, it can be read as a locale policy constraint without user choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.