Back to skill

Security audit

雀阴·平衡魄

Security checks for vulnerabilities and agentic risk

Overview

This skill is a markdown-only scheduling guide with no code execution, persistence, credential access, or hidden data handling.

Install this if you want Chinese-language task scheduling and resource-allocation guidance. Review the broad trigger phrasing if unintended activation would be disruptive in your workflow.

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 (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The natural-language content of the skill is effectively Chinese-only, including the description, usage guidance, output format, and operational rules. Under the policy, forcing a specific language without user opt-in is a language/locale policy violation unless the locale restriction is clearly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger examples are broad enough that ordinary user statements about handling multiple tasks or high system load could activate the skill unintentionally. In an agent system, unintended activation can alter planning or resource-allocation behavior without explicit user intent, creating reliability and policy-enforcement risks even if no direct code execution is present.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.