Back to skill

Security audit

novel-writer

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese urban sci-fi writing assistant made of Markdown guidance, with only minor over-activation and style-scope caveats.

Install this if you want Chinese Tomato-style urban sci-fi writing help. Be aware that its broad trigger words and strong style rules may make it less suitable for neutral, multilingual, or non-urban-sci-fi fiction unless you explicitly ask the agent to use a different style.

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
  • 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 (9)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The README states that the skill will automatically activate when any listed keyword appears, but it does not define scope, matching rules, or constraints. This ambiguity increases the chance of accidental invocation, making the assistant behavior less predictable and easier to trigger unintentionally through normal discussion.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list contains very broad, common phrases such as 写小说, 情节设计, and 角色塑造 that can appear in ordinary conversation. In an auto-activation system, this can cause the skill to load unexpectedly, which may override user intent, inject irrelevant instructions, or expose the conversation to unintended prompt-scope expansion.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill description hard-codes a 'Tomato Platform style' specialization without presenting it as an optional mode or requiring user opt-in. In practice, this can bias outputs toward a specific platform aesthetic even when the user asked for general fiction help, reducing user control and potentially causing policy or quality mismatches rather than a direct security compromise.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger list includes broad terms such as '写小说', '小说创作', and '角色塑造' that are not tightly scoped to this skill’s specific urban sci-fi niche. This can cause unintended invocation for general writing requests, leading to skill overreach, user intent mismatch, and inappropriate application of its strong stylistic constraints.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file is entirely framed as a Chinese writing guide, and later explicitly requires '语言口语化,没有翻译腔', which prescribes a specific language/locale style. Under the policy rule, forcing a language without user opt-in is a natural-language policy concern unless the locale restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file contains user-facing instructional content exclusively in Chinese, beginning with the title at L001 and continuing throughout the file. Under the policy rule for natural-language violations, forcing a specific language without user opt-in or clear justification is a reportable issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The file title and all instructional content are written exclusively in Chinese, with no indication that language choice is optional or that the skill is intended only for a Chinese-language audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The skill documentation is entirely in Chinese and all examples, commands, and interaction guidance assume Chinese-language usage, but the file does not state that the skill is region-specific or offer an opt-in language choice. Under the policy, forcing a specific language without user choice can be a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

SQP-3 applies to all file types and covers natural-language policy violations such as forcing a specific language without user opt-in. This style guide presents all instructions in Chinese with no indication that users can choose another language or that the locale restriction is justified.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.