Back to skill

Security audit

古诗词新民谣改编

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language creative writing skill for adapting classical poetry into modern folk lyrics, with no executable code, persistence, credential use, or hidden data access.

Install this if you want a Chinese-focused poetry-to-folk-lyrics writing assistant. Non-Chinese users may need to explicitly ask for another language, and users planning public release should separately review copyright and platform rules for any source poems, references, or generated lyrics.

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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill hardcodes Chinese-language behavior across its description and output requirements without indicating that it should adapt to the user's preferred language. This can reduce usability, cause unexpected behavior for non-Chinese users, and make the agent ignore higher-level localization or accessibility expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The entire skill manual is written in Chinese and all examples, requirements, and stylistic instructions assume Chinese-language lyric composition. There is no indication that the user can opt into another language or that the locale restriction is explicitly justified as a region-specific tool, which fits the language/locale policy violation category.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The heading and template explicitly require the Style Prompt to be in English, even though the rest of the document is in Chinese. This imposes a language policy choice on users without opt-in or explanation, which matches the locale/language policy violation criteria.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.