Back to skill

Security audit

漂流瓶

Security checks for vulnerabilities and agentic risk

Overview

This skill only returns a random preset Chinese inspirational message and does not access data, network services, credentials, or persistence.

Install this if you want Chinese drift-bottle style inspirational messages. Be aware it may trigger from general inspiration or life-reflection prompts, and it does not provide non-Chinese output unless modified.

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
95% confidence
Finding

The skill declares broad trigger phrases such as “随机消息”, “获取灵感”, and “人生感悟”, which overlap with common conversational requests and can cause the skill to activate when the user did not explicitly intend to invoke it. This is dangerous because unintended activation can hijack normal conversation flow, reduce user control, and cause the agent to execute skill behavior in irrelevant contexts.

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 metadata and behavior are presented entirely in Chinese and imply Chinese-language responses, but they do not state any user-choice mechanism or fallback for other languages. This can lead to unexpected language output, confusing users and causing the skill to respond in a language the user did not request or understand.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This Python skill's docstrings and all generated user-facing messages are written in Chinese, and the program always prints Chinese output regardless of user preference. That is a natural-language locale policy concern because the file does not provide opt-in, fallback, or documentation justifying a Chinese-only audience.

Content

No source excerpt is available for this finding.