Back to skill

Security audit

Novel Writer Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward novel-writing helper with no code execution, permissions, hidden data access, or persistence mechanisms.

Installers should know this skill may answer in Chinese by default and may activate on broad story-writing terms. Ask for English or a narrower style when needed.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The instruction 'Default to Chinese output unless the user asks for another language' imposes a language preference by default rather than offering a neutral choice. The policy allows explicit user choice or justified locale constraints, but this line applies a default language globally without opt-in or documented necessity.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest uses several generic activation keywords such as "novel," "story," "chapter," "outline," and "plot" without constraining context or providing exclusion conditions. These broad terms can overlap with common writing or discussion requests, increasing the risk of unintended skill invocation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
97% confidence
Finding

The template instruction at L006 is written as a direct prompt in Chinese, and the rest of the file's template fields are also presented only in Chinese. This imposes a specific language/locale on users without any visible opt-in or alternative language option, which matches the language-policy concern for natural-language content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest mixes English and Chinese trigger keywords, but there is no documentation indicating that multilingual behavior is optional, user-selected, or region-specific. This can create an implicit language/locale policy issue because the skill is configured to activate on a specific language set without stating how language preference is handled.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.