玄幻小说创作主编

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 9:30 AM UTC
• Version: 1.0.0

Overview

This is a disclosed Chinese fantasy-novel writing workflow that creates local project files, with no evidence of hidden data access, exfiltration, or destructive behavior.

Install only if you want an autonomous Chinese-language xuanhuan novel workflow that may create many local markdown files and a final TXT output under its workspace. Review or back up existing files in that workspace before use.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (13)

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The activation criteria are extremely broad and include many common phrases, causing the skill to trigger for loosely related requests without clear user intent. In a skill that then autonomously performs multi-step orchestration and file-producing workflows, this increases the risk of unexpected execution, user confusion, and unintended side effects.

Natural-Language Policy Violations

Medium

• Confidence: 82% confidence
• Finding: The skill is presented entirely as a Chinese-language creative editor workflow and does not indicate that users may choose another language or opt in to Chinese output. Under SQP-3, forcing a specific language without user choice is a natural-language policy concern unless the locale constraint is explicitly justified.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The README explicitly says the skill will automatically scan the workspace and continue from existing files, while also producing files in designated directories, but it provides no user-facing warning, consent step, or scope limitation. In an agent setting, silent filesystem reads and writes can expose unrelated local content, cause unintended data reuse, or overwrite user files without the user realizing the skill accesses the workspace.

Natural-Language Policy Violations

Medium

• Confidence: 73% confidence
• Finding: The entire skill is written to operate in Chinese and instructs a Chinese-language creative workflow, but it does not state that this locale is optional or restricted by design. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is clearly documented and justified.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill instructs the agent to create a workspace, write multiple files, and emit a final TXT artifact automatically, but it does not require notifying the user or obtaining consent before modifying the filesystem. This can lead to unexpected persistence of content, clutter, or overwriting/creating files in shared environments.

Natural-Language Policy Violations

Medium

• Confidence: 91% confidence
• Finding: The entire skill persona and required output format are specified only in Chinese, and there is no indication that the user may choose another language. This creates a language-policy concern because the skill appears to require a specific language by default rather than offering localization or opt-in.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: The file mandates a fixed response format entirely in Chinese, including the required heading and section labels. This is a natural-language locale constraint, and the skill does not provide user opt-in or explain that it is intentionally limited to Chinese-language use.

Natural-Language Policy Violations

Medium

• Confidence: 93% confidence
• Finding: The skill content is written entirely in Chinese and prescribes a Chinese-only role/output style without any mechanism to adapt to the user's language. This can override user preference, reduce transparency, and create usability or safety issues if critical instructions, refusals, or policy-relevant guidance are delivered in a language the user does not understand.

Natural-Language Policy Violations

Medium

• Confidence: 92% confidence
• Finding: The entire skill is written as a mandatory Chinese-language persona and output specification, with no indication that users may choose another language. This creates a language/locale policy concern because it imposes a specific language by default rather than offering opt-in or documenting a region-specific need.

Natural-Language Policy Violations

Medium

• Confidence: 82% confidence
• Finding: The file is entirely written as a prescriptive skill prompt in Chinese and defines the role directly in that language, with no indication that the user may choose another language. Under the policy, forcing a specific language without opt-in is a natural-language policy concern unless the locale constraint is explicitly justified.

Natural-Language Policy Violations

Medium

• Confidence: 90% confidence
• Finding: The instructions require full-width Chinese punctuation and specific quotation conventions, which imposes a language/locale formatting policy. Because the file does not state that this is optional or limited to a clearly justified locale-specific context, it appears to force one locale standard without user opt-in.

Missing User Warnings

Low

• Confidence: 85% confidence
• Finding: This markdown skill explicitly instructs the agent to save output to `assets/output/[小说名].txt`, which affects the local filesystem. The description does not include any warning or disclosure to the user about creating or overwriting files, so the file-write behavior is not surfaced.

Natural-Language Policy Violations

Low

• Confidence: 89% confidence
• Finding: The shell command publishes the skill with the fixed name "玄幻小说创作主编", which implies a specific language/locale choice embedded directly in the artifact metadata. There is no indication in this file that users can opt into this locale or that the skill is intentionally region-specific, so it may violate the language/locale policy requirement.

Static analysis

No suspicious patterns detected.