Back to skill

Security audit

GuruWalk Free Tours Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow GuruWalk tour-search helper with no local code execution, installs, persistence, or credential access, though users should know it sends tour search details to an external MCP server.

Install only if you are comfortable with tour search parameters such as city, date range, and language being sent to the GuruWalk MCP service. When requests are vague, ask the agent to confirm before searching.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill advertises broad trigger phrases like 'plans in a city' and general tour-related requests, which can cause the agent to invoke this external integration during ordinary travel conversation where the user did not specifically ask to query GuruWalk. That increases the chance of unnecessary third-party data disclosure and tool use without clear user intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs the agent to use an external MCP endpoint but does not clearly warn that user-supplied city, dates, and language will be transmitted to a third-party service. This creates a transparency and privacy risk because users may disclose itinerary information without realizing it will leave the primary system.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The defaults section forces en whenever the conversation is not Spanish, even if the user has not requested English tour results. This is a locale/language policy concern because it imposes a language preference without explicit user choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.