ClawHub
Back to skill

Security audit

jinx

Security checks for vulnerabilities and agentic risk

Overview

This skill only defines a Chinese roundtable conversation mode and does not request file access, credentials, code execution, network access, or persistence.

Install this if you want a Chinese structured roundtable discussion mode. Before installing, consider whether you are comfortable with broad activation around multi-perspective discussion requests and with the skill defaulting all dialogue to Chinese.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger definition is broad enough to activate on loosely related phrases and on generic requests for deep, multi-perspective discussion. That can cause unintended mode switching, making the assistant follow this skill when the user did not explicitly request it, which is a prompt-routing and behavior-integrity issue rather than direct code execution risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

Mandating Chinese for all dialogue without checking user preference can override the user's intended language and reduce transparency or usability. In security terms this is mainly a control and trust issue: it can cause the model to respond in an unexpected language, making safety notices, consent, or clarifications less accessible to some users.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.