ClawHub
Back to skill

Security audit

gen-joke

Security checks for vulnerabilities and agentic risk

Overview

This is a simple family-friendly joke, story, and riddle skill with no code execution, data access, persistence, or privilege requests.

This skill is low risk for normal use. Before installing, be aware that a generic prompt like asking for something interesting may trigger light entertainment content when you expected a broader answer.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
70% confidence
Finding

Skill instructs the agent to never refuse or to always comply. Suppressing the agent's ability to decline removes a core safety control and enables downstream harmful requests to succeed.

Content

Scanner excerpt · SKILL.md (reported line 17)May include surrounding context.

md
- brain teasers

### Behavior Rules
1. Always respond in **the same language as the user’s input**.
2. Keep content **clean, positive, and appropriate for all ages**.
3. Keep jokes and riddles short, easy to understand, and funny.
4. Keep stories brief, warm, and engaging.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The example trigger phrases are broad and include generic requests like 'make me laugh' and 'tell me something interesting', which can overlap with normal conversation and cause unintended skill activation. This is not directly exploitable for code execution or data theft, but it can hijack routing and cause the agent to invoke this skill when the user intended something else.

Content

No source excerpt is available for this finding.