ClawHub
Back to skill

Security audit

Dad Jokes

Security checks for vulnerabilities and agentic risk

Overview

This skill simply fetches one dad joke from a public HuggingFace dataset when the user asks for humor.

Installers should be aware that ordinary requests for something funny may cause a small external network request to HuggingFace; otherwise the skill is narrow and does not ask for sensitive access.

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
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger conditions are excessively broad, covering generic requests like 'tell me something funny' or 'I need a laugh,' which can cause the skill to activate in situations where the user did not specifically ask for this external-data-backed behavior. That creates unnecessary tool use and network access, increasing the chance of unintended invocation and reducing user control over when the skill runs.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.