ClawHub
Back to skill

Security audit

Jinko

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward flight and destination search helper that uses a disclosed external Jinko MCP server, with no local code execution or persistence.

Before installing, be aware that flight-search inputs and travel preferences may be sent to the Jinko MCP server. Use it for flight searches or destination discovery, and avoid sending sensitive personal travel details unless you are comfortable sharing them with that service.

A.I.G

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

SkillSpector

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger language is broad enough to activate on generic travel-planning requests, which can cause the agent to invoke this skill when the user did not specifically ask for flight search or destination discovery. In context, that creates unnecessary sharing of user itinerary, location, budget, or preference data with an external MCP service and may bias the assistant toward this integration over safer or more appropriate responses.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs the agent to connect to and use an external MCP server but does not provide a user-facing disclosure that travel queries and associated preferences will be transmitted off-platform. Because flight searches commonly include sensitive contextual data such as origin city, dates, budget, and travel interests, the lack of transparency undermines informed consent and increases privacy risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.