ClawHub
Back to skill

Security audit

Tell Jokes

Security checks for vulnerabilities and agentic risk

Overview

This skill only gives the agent instructions for telling jokes, with no code, tools, credentials, persistence, or data access.

Before installing, consider whether you want a humor skill that may activate for vague boredom or cheering-up requests; otherwise it appears low risk and self-contained.

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

Medium
Confidence
96% confidence
Finding
The skill description uses very broad activation phrases like 'wants to be cheered up,' 'says they're bored,' and 'requests something funny,' which can overlap with ordinary conversation and cause the skill to trigger when the user did not explicitly ask for it. This creates an overbroad routing surface that may hijack unrelated interactions or interfere with higher-priority skills, though the direct security impact is limited because the skill only tells jokes.

Static analysis

No suspicious patterns detected.