ClawHub
Back to skill

Security audit

Lyrical Fable

Security checks for vulnerabilities and agentic risk

Overview

This is a creative-writing style skill with broad routing language, but it does not request sensitive access, run code, persist changes, or move data.

Install this if you want a persistent lyrical-fable writing mode available for creative fiction. Be aware that its routing language is broad, so it may influence ordinary poetic or philosophical story requests even when you did not explicitly ask for this exact style.

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
Confidence
87% confidence
Finding
The manifest description uses ambiguous activation language spanning several common creative-writing intents, making it likely this skill will be selected for a wide range of ordinary story-writing requests. This is risky because broad routing criteria increase unintended invocation and can cause style- or instruction-heavy behavior to be applied outside its intended niche.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger condition is broad enough to match many generic creative-writing requests, which can cause the skill to activate when a user did not clearly ask for this specific behavior. Over-broad activation is dangerous because it can override more appropriate skills or system behavior, leading to misrouting, unexpected style imitation, or policy-sensitive responses being handled by the wrong prompt template.

Static analysis

No suspicious patterns detected.