ClawHub
Back to skill

Security audit

Writers Room Story Engine

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed creative-writing orchestration skill with no evidence of hidden execution, data access, persistence, or destructive behavior.

Before installing, understand that this skill will tend to structure story requests through planning, diagnosis, and staged development before prose. That behavior is intentional and disclosed; no sensitive system access was found.

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
92% confidence
Finding

The trigger phrase 'when a user asks for story help' is broad enough to overlap with many general creative-writing requests, making the orchestration skill likely to activate when a more specific skill would be safer or more appropriate. In a multi-skill agent, this can cause misrouting, unnecessary interception of prompts, and reduced predictability of which instructions govern the response.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.