ClawHub
Back to skill

Security audit

Story Teller

Security checks for vulnerabilities and agentic risk

Overview

This skill only provides storytelling guidance and does not ask for files, credentials, commands, network access, or persistent changes.

Before installing, expect this skill to influence creative story-writing requests and possibly activate for a wide range of storytelling prompts. It does not appear to access private data, run code, install dependencies, or persist changes.

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
93% confidence
Finding
The skill description contains very broad, everyday trigger terms such as writing stories, bedtime stories, short fiction, dramatic scenes, and family-safe stories, which creates loose invocation boundaries. In agentic environments, this can cause the skill to activate in many general writing contexts where a more appropriate or safer skill should handle the request, increasing prompt-routing confusion and unintended behavior.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The manifest's default prompt says to "Use $story-teller to write a vivid, catchy story..." but does not define when this skill should or should not activate beyond a general writing request. Because the invocation scope and exclusions are not specified, the trigger could overlap with ordinary requests for storytelling and cause unintended activation.

Static analysis

No suspicious patterns detected.