Back to skill

Security audit

seo-maps

Security checks for vulnerabilities and agentic risk

Overview

This maps SEO skill is coherent and disclosed, with only minor cautions about a broad trigger and a saved report file.

Use this skill when you intentionally want local maps SEO analysis. Prefer invoking it with /seo maps or another explicit maps-SEO request, review any paid API confirmation before proceeding, and remember that the generated Markdown report may contain business/location and competitive-analysis data.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger phrase "maps" is so broad that it can activate on many ordinary user requests unrelated to this skill’s intended scope. Over-broad invocation increases the chance of unintended tool use, unnecessary external API calls, and accidental disclosure or persistence of user-provided business/location data during an analysis the user did not actually request.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill explicitly generates a file containing analysis results but does not warn the user that output will be written to disk. This can create an unexpected persistence/privacy issue because business identifiers, locations, review intelligence, competitive analysis, and possibly API-derived data may be stored locally without informed user consent.

Content

No source excerpt is available for this finding.