Back to skill

Security audit

Relationship Nurture Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language relationship-advice skill with no evidence of hidden access, persistence, exfiltration, or destructive behavior.

Before installing, be aware this skill appears intended for Chinese-language relationship guidance and may activate on broad relationship terms; it should not be treated as professional therapy, legal, medical, or safety advice.

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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README’s substantive instructions and examples are entirely in Chinese, which effectively forces a specific language for users. Under the policy rule, a language constraint should either be optional for the user or clearly justified as region- or locale-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill content is effectively Chinese-only, with no user language negotiation or stated locale constraint. While not a classic security flaw, this can cause misunderstanding of emotionally sensitive advice, incorrect task routing, or exclusion of users who did not intend to interact in Chinese.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger phrases are broad, generic relationship terms like '夫妻关系' and '不知道怎么处理关系', which can cause the skill to activate in many loosely related conversations without clear user intent. In a relationship-advice context, unintended activation can surface sensitive emotional guidance when the user did not request it, increasing privacy, relevance, and trust risks.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file’s natural-language content, labels, examples, and output strings are entirely in Chinese, and the parsing logic only recognizes Chinese relationship and emotion keywords. There is no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking context, which creates a locale policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest uses the description "auto-generated skeleton," which provides no specific activation scope, trigger context, or constraints for when this skill should be used. In a manifest file, such an underspecified description can contribute to ambiguous invocation behavior because it does not distinguish this skill from unrelated requests or define exclusion conditions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.