Security audit

爆款小说开篇

Security checks for vulnerabilities and agentic risk

Overview

This is a narrowly scoped Chinese fiction-writing helper with no code execution, credential access, persistence, or hidden data handling.

Install this if you want a Chinese short-fiction hook generator. Be aware it may activate automatically for similar fiction-opening requests, but the inspected files only affect writing style and output format, not your files, accounts, credentials, or system settings.

SkillSpector

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)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: Line L03 starts with one specific trigger phrase but then broadens activation to users who ask for 'five selectable opening leads, short-novel hook options, opening-guide variants, or a final Chinese fiction copy under 200 characters'. These descriptions are not an explicit bounded trigger list and could overlap with ordinary writing-assistance requests, making it unclear when this skill should activate versus a more general writing skill.

Natural-Language Policy Violations

Low

Confidence: 90% confidence
Finding: Line L29 instructs the skill to 'Write in Chinese unless the user asks otherwise,' establishing a forced default language choice. Under the policy, locale or language constraints should be user-selected or clearly justified; here the skill is Chinese-focused, but it does not explicitly require or confirm user opt-in before enforcing that default.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: This manifest enables implicit invocation but provides no explicit trigger phrases, scope limits, or exclusion conditions. Combined with broad descriptive text, this makes it unclear when the skill should activate versus not activate, increasing the risk of unintended invocation.

Natural-Language Policy Violations

Medium

Confidence: 97% confidence
Finding: The default prompt explicitly instructs the skill to produce Chinese short-fiction hooks and final copy, but there is no indication that the user can choose another language or opt into this locale constraint. This is a natural-language policy concern because it imposes a specific language by default.

Static analysis

No suspicious patterns detected.