Back to skill

Security audit

Zhiyanzhai Research 脂砚斋是谁

Security checks for vulnerabilities and agentic risk

Overview

This is a narrowly scoped Chinese literature research-writing skill with disclosed web research and markdown output behavior, and no evidence of hidden execution, persistence, credential access, or destructive actions.

Install this if you want a focused Simplified Chinese research-writing assistant for Zhiyanzhai and Dream of the Red Chamber. Be aware that it is intentionally scoped to Chinese output and depends on web research quality, so users should still verify citations and claims before academic use.

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
96% confidence
Finding

The description states the skill will generate the research article in Simplified Chinese, which imposes a language choice by default. Because this is a general research/content-generation skill rather than a clearly region-specific compliance tool, forcing a specific language can violate language/locale policy unless the user explicitly opts in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The 'Do not use this skill for' section excludes articles in languages other than Simplified Chinese, which is a natural-language policy concern because it denies language choice rather than offering opt-in. There is no documented justification that this locale restriction is necessary for a narrowly scoped regional or compliance use case.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The style guide says '全文使用简化中文', which is an unconditional language requirement embedded in the skill instructions. This is a locale-policy issue because the skill does not present language as an option or require explicit user consent to constrain output to one language.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.