ClawHub
Back to skill

Security audit

Professional Novel Writing Techniques

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown novel-writing guidance skill with no code execution, credential access, persistence, or hidden data flows.

Safe to install for fiction-writing help. Be aware it may activate on some broad writing or character-design requests, so users who maintain many writing skills may prefer narrower routing, but no hidden or high-impact behavior 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation guidance is broad enough to match many generic writing-related prompts, such as character design or language refinement, which can cause the skill to be invoked outside a clearly bounded scope. While this is not directly a code-execution or data-exfiltration issue, over-broad triggering can override more appropriate skills, create unintended behavior, and expand the attack surface for prompt-routing mistakes.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

Line L10 instructs authors to define a character's 'dialect or professional jargon' as part of the linguistic fingerprint. Because SQP-3 covers language or locale policy violations in natural language, this can be read as encouraging a fixed language variety without any opt-in or user choice.

Content

No source excerpt is available for this finding.