Back to skill

Security audit

JACK

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language weather helper that uses search for weather data and does not show hidden, persistent, or destructive behavior.

Install this if you want a Chinese-language weather helper. Be aware it may respond in Chinese and may activate on broad weather, temperature, or clothing-advice requests; it relies on search results for current weather.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill is written to operate and respond in Chinese without stating that this is conditioned on user language preference or locale. This can cause mismatched-language responses, reduce transparency, and degrade safe operation for users who may not understand the output or the follow-up questions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger conditions are broad enough to match common conversation about weather, temperature, or clothing advice, which can cause the skill to activate unexpectedly. This is primarily a scope/control issue rather than a direct security exploit, but it can lead to unintended tool use and user confusion if the agent invokes search without clear intent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest says the skill applies whenever the user asks about weather, but it does not define specific trigger phrases, scope constraints, or exclusion cases. This is broad enough to overlap with ordinary conversation and could cause unintended invocation when weather is mentioned casually.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The natural-language description and skill behavior are written only in Chinese, which can imply a fixed language experience without stating that the user can choose another language. The file provides no opt-in or justification that this is a region-specific skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.