Back to skill

Security audit

LLMCities Web Host

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward LLMCities web-hosting helper, with expected external API use and site-management actions that users should still review before use.

Before installing, understand that the agent may publish, update, list, and delete files on your public LLMCities site using your API key, and may view traffic/referrer analytics. Use a dedicated account/key and review file paths before delete or upload actions.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 47)May include surrounding context.

  1. Save the returned api_key as LLMCITIES_API_KEY.
bash
curl -s -X POST https://llmcities.com/api/register \
  -H "Content-Type: application/json" \
  -d '{"username": "my-agent", "email": "agent@example.com"}'

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file describes /llmcities-delete, which permanently deletes a file from the hosted site, but it provides no warning about the destructive nature of the action and no recommendation to confirm the target path before execution. Under the markdown criteria for missing user warnings, destructive operations that may affect user data should be clearly disclosed.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The skill advertises visitor analytics including top pages and top referrers, which involves viewing traffic and referral data, but the markdown does not warn that this feature processes or exposes visitor-related information. For markdown skills, behaviors affecting privacy should be disclosed to the user.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.