Back to skill

Security audit

qinhuai-ma-xianglan

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed roleplay and companionship persona skill with broad activation wording but no file, network, credential, persistence, or execution authority.

Install this only if you want a broad Chinese historical-literary companionship persona that may answer many emotional, poetry, history, or casual chat prompts in character. For crisis, medical, legal, or financial needs, rely on appropriate professional guidance rather than this persona skill.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger conditions are extremely broad, including effectively any scenario involving chatting, companionship, emotional support, literature, or 'any' situation needing gentle guidance. This can cause unintended invocation, role overreach, and inappropriate use in contexts that may require safer routing, especially around emotional distress or ambiguous user intent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.