Back to skill

Security audit

Joke

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese joke-telling skill with no code execution, data access, persistence, or hidden behavior.

This skill appears safe to install for users who want Chinese humor responses. Expect it to answer in Chinese and possibly activate on broad humor or cheer-up requests; users who want multilingual joke handling may prefer a more explicit locale-aware skill.

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 trigger description is broad enough to match many ordinary conversational requests involving humor or cheering someone up, which can cause the skill to activate in contexts where the user did not explicitly want this specialized behavior. Unintended invocation can override more appropriate skills or responses, creating reliability and policy-scope issues even though the content itself is low risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill is written to operate in Chinese only and does not provide any language negotiation or fallback behavior. This can lead to incorrect or inaccessible responses when invoked by users speaking other languages, especially if broad triggers cause activation outside a Chinese-language context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The slug joke-teller-cn suggests a China/Chinese-specific locale variant, but this manifest provides no natural-language documentation indicating user choice, opt-in, or a justified region-specific purpose. Under the stated policy, locale constraints should be explicitly offered as a choice or clearly documented when they are region-specific.

Content

No source excerpt is available for this finding.