Back to skill

Security audit

Shuangwen Rebirth

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese interactive fiction roleplay skill with no executable code or hidden system access, though its trigger wording is somewhat broad.

Install this if you want a Chinese-language rebirth-story roleplay assistant. Be aware that broad phrases like 'I want to be reborn' in Chinese may trigger it, and using '存档' may save story progress in agent memory.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list includes broad everyday phrases such as “我要穿越 / 我要重生”, which can plausibly appear in normal conversation outside an explicit request to invoke this skill. That raises the chance of unintended activation, causing the assistant to switch into roleplay mode unexpectedly and override the user’s actual task context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file presents the skill content in a single forced language, beginning with a Chinese-only title and continuing throughout the document. Under the language/locale policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description uses open-ended wording like “等时触发此技能”, which leaves the activation boundary undefined. In practice, vague trigger scope can cause overmatching by routing logic, leading to accidental invocation on semantically similar phrases the user did not intend as a command.

Content

No source excerpt is available for this finding.