ClawHub
Back to skill

Security audit

cool

Security checks for vulnerabilities and agentic risk

Overview

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

Install this if you want a playful helper for names, slogans, ASCII art, and fun comments. Be aware it may add flair or emojis when used, so ask for a plain or professional tone when that matters.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation text is broad enough that ordinary creative requests could implicitly trigger the skill’s behavioral override, causing the assistant to adopt this mode without clear user consent. While not directly exfiltrating data or executing actions, it can unpredictably steer responses and override normal instruction-priority expectations in multi-skill environments.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The prompt mandates a fixed creative/stylish response format without giving the user a choice to decline or request a different tone. This is risky because it can conflict with user preferences or higher-priority system behavior, reducing controllability and making the assistant more susceptible to prompt-steering through the skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.