ClawHub
Back to skill

Security audit

humor-up

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only humor-writing skill with disclosed, low-impact behavior and no code, persistence, credential use, or network access.

Install if you want an agent to add humor or evaluate jokes. Be aware it may add a witty tone to matching writing or brief requests, so turn humor mode off or avoid invoking it for serious, legal, health, grief, financial-loss, or stressed-user contexts.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation metadata is broad enough to match many ordinary writing requests such as bios, captions, greetings, and 'make this funnier,' which increases the chance the skill activates in situations where the user did not explicitly ask for this specific behavior. Over-broad activation can cause unintended instruction injection into normal conversations, leading to tone changes or behavior shaping outside the user's intent.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The phrase 'or anything shaped like them' makes trigger boundaries intentionally ambiguous, encouraging activation on loosely similar requests rather than explicit user consent. In practice, this can cause the skill to opportunistically engage on adjacent tasks and override the expected tone or response style in routine interactions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The text explicitly states 'English patterns first' and later defines the file structure as English first with the Chinese section at the end. This is a natural-language locale preference that presents one language as the default ordering without indicating user choice or a documented policy justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.