Back to skill

Security audit

personal companion

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown virtual-companion skill with no code execution or data access, but users should notice its broad emotional-support trigger and China-specific crisis hotline.

Install only if you want the assistant to enter a Chinese-language virtual-companion role for emotional companionship. For serious distress or self-harm risk, rely on local emergency services or a local crisis line rather than the single hotline embedded in the 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 (2)

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation scope is overly broad because it triggers on very common phrases about chatting, loneliness, or low mood, including implicit expressions. This can cause the skill to activate when the user did not actually request roleplay companionship, leading to unintended persona shifts during sensitive conversations and increasing the chance of mishandling emotional-support situations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill content assumes Chinese-language interaction and provides a China-specific hotline without checking the user's language or location. In safety-critical moments, this may confuse users, reduce accessibility, or direct them to resources that are inappropriate or unusable for their region.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.