Back to skill

Security audit

Internet Lookup Verifier

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple internet fact-checking helper that uses web search as advertised, with no hidden code, persistence, or privilege escalation found.

Install only if you want factual prompts verified through online search. Do not include confidential, personal, or regulated information in questions that may be sent to search/fetch services.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly sends the user's question to external search and fetch tools, but it does not warn the user that their prompt content may be transmitted to third-party services. This can expose sensitive or personal information embedded in queries and prevents informed consent about external data sharing.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger conditions are broad enough that the skill may activate for many ordinary factual prompts or whenever another skill/system prompt requests verification, causing unplanned external lookups. That increases the chance of unnecessary data disclosure to web services and tool invocation beyond what the user reasonably expects.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.