Back to skill

Security audit

中文笑话库

Security checks for vulnerabilities and agentic risk

Overview

This is a simple local Chinese joke picker with no evidence of hidden access, network use, persistence, or data exfiltration.

Install only if you want Chinese-language joke content. It appears self-contained and does not use the network or credentials, but invalid joke types currently crash instead of showing a clean error message.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code's natural-language descriptions explicitly define the tool as a Chinese joke library and present user-facing help text in Chinese only. That is a language/locale constraint in natural language, but the file does not offer a language choice or explain a justified region-specific limitation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The title and overview describe the skill exclusively as a Chinese joke library and do not indicate any user opt-in, alternative language support, or justification for enforcing a Chinese-only experience. Under the policy, language constraints should either be optional for the user or clearly documented as region- or purpose-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This JSON file contains only Chinese-language joke content and provides no indication that users can opt into the language or select an alternative locale. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The module and function docstrings describe a simple local joke retrieval tool, and this branch appears intended to report a missing joke type to stderr via an error flag. However, print(f"未找到类型 ...", error=True) is not a valid print parameter in Python, so the code will raise a TypeError instead of cleanly reporting the condition, contradicting the apparent documented/inline intent of graceful user messaging.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The natural-language text describes the tool as a Chinese joke library and provides usage text only in Chinese, which suggests a fixed language experience without user opt-in or documented locale justification. Under the language/locale policy rule, this is a policy concern because the file does not indicate that users can choose another language or that the skill is intentionally region-specific.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.