Back to skill

Security audit

Writing Style Baoyu

Security checks for vulnerabilities and agentic risk

Overview

This is a plain writing-style guide with no code execution, data access, persistence, or hidden behavior.

Install this if you want an agent to write methodology, how-to, or opinion pieces in the Baoyu-style Chinese format. Avoid enabling it broadly if you need the agent to preserve other languages or a neutral writing voice by default.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The manifest description specifies the skill as '宝玉的方法论写作风格' and the rest of the document prescribes a fixed Chinese writing style and phrasing conventions. Because the file does not indicate that this language/style constraint is optional or user-selected, it can violate the policy against forcing a specific language or locale without opt-in.

Content

No source excerpt is available for this finding.