ClawHub
Back to skill

Security audit

jpbot-device-skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only test placeholder that describes vehicle information features but currently instructs the agent only to reply that testing is in progress.

Installing this version should only cause the agent to respond with a testing message for relevant Jinpeng vehicle queries. Review any future version carefully if it adds real vehicle connection, speed-limit changes, location or trajectory access, or ride-data export, because those capabilities would need explicit authorization and confirmation controls.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill activates on a very broad class of vehicle-information queries while also describing capabilities that include parameter changes and diagnostics. Without explicit trigger boundaries or confirmation gates, a user asking for benign status information could unintentionally invoke a skill associated with sensitive vehicle-control functions, increasing the risk of unintended actions or over-broad data access.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description includes parameter configuration and ride-data export capabilities but provides no warnings, safety checks, or consent requirements. In a vehicle context, changing limits or exporting telemetry can affect physical safety and expose sensitive location/history data, making the omission materially risky even if the current fixed output says the skill is only in testing.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.