ClawHub
Back to skill

Security audit

Clean Dad Jokes

Security checks for vulnerabilities and agentic risk

Overview

This is a simple humor-writing skill with no code execution, data access, persistence, or hidden behavior.

This skill is suitable for generating clean jokes and captions. Users should expect it to influence style for some general family-friendly humor requests, not just explicit dad-joke prompts.

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
  • 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 (1)

Vague Triggers

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The activation guidance says to use the skill for requests like 'simple funny captions' and 'family-friendly humor,' which are broad phrases that could match many ordinary writing requests beyond dad jokes. The file does not provide exclusion conditions or negative examples to clarify when the skill should not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.