Bilibili Creator Cn

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 8:24 PM UTC
• Version: 1.0.0

Overview

This skill is a low-risk Bilibili creator helper that runs local scripts and prints mostly static advice, though it should not be mistaken for live AI or data analysis.

Install only if you want a lightweight, Chinese-language Bilibili advice helper. Treat its recommendations and creator statistics as generic or simulated guidance, not live platform analytics or verified data.

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

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (10)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 94% confidence
• Finding: The description promises a creator assistant with several substantive capabilities: tag recommendations, posting time guidance, title optimization, and UP analysis. The supplied code only prints a canned report for any provided UP name and does not fetch data, analyze content, optimize titles, or generate recommendations dynamically. While the script is related to 'UP analysis' in theme, its actual behavior is materially narrower and largely simulated, so the declared description overstates the implemented functionality.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 94% confidence
• Finding: The code only implements one narrow part of the declared description: tag and category recommendations for several content types. It does not provide any functionality related to posting times, title optimization, or UP analysis. There are no extra dangerous or undeclared permissions/resources used, but the declared description overstates the implemented behavior, so this is a material description-behavior mismatch.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 92% confidence
• Finding: The supplied code chunk is narrowly focused on title optimization, which is one part of the declared description. However, the declared purpose describes a broader creator assistant with tag recommendations, posting times, and UP analysis. This code does not implement those additional capabilities, nor does it access resources or triggers inconsistent with title optimization. Because the description materially overstates the functionality represented by this code chunk, there is a description-behavior mismatch for this chunk.

Natural-Language Policy Violations

Medium

• Confidence: 90% confidence
• Finding: The skill is presented as a Bilibili creator assistant and the examples/use cases are written in Chinese-centric terms, indicating a locale-specific experience, but the documentation does not state that the skill is limited to Chinese-language/Bilibili contexts or offer any user choice of language/locale. Under the policy, forcing a specific language or locale without opt-in should be flagged unless clearly documented and justified.

Natural-Language Policy Violations

Medium

• Confidence: 98% confidence
• Finding: The script's user-facing output and usage instructions are presented only in Chinese, which imposes a specific language on all users. Under the policy, forcing a language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified, which is not present here.

Natural-Language Policy Violations

Medium

• Confidence: 94% confidence
• Finding: This shell script presents all user-facing instructions and output exclusively in Chinese, including the usage line and all recommendations. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.

Natural-Language Policy Violations

Medium

• Confidence: 93% confidence
• Finding: All user-facing comments and output strings are in Chinese, and the script provides no option to select another language or opt in to this locale. Under the policy, forcing a specific language without user choice is a natural-language policy violation unless the locale restriction is clearly justified.

Natural-Language Policy Violations

Low

• Confidence: 78% confidence
• Finding: The document is explicitly tailored to Bilibili creators and uses Chinese-specific platform terminology throughout, but it does not mention any language or locale selection or opt-in. Under the policy rule, forcing a specific language/locale without user choice can be a natural-language policy concern unless the locale restriction is clearly documented and justified.

Natural-Language Policy Violations

Low

• Confidence: 76% confidence
• Finding: The package metadata names the skill "bilibili-creator-cn" and includes the keyword "china", which suggests a locale-specific focus. Because the file does not clarify whether the skill enforces Chinese language or regional behavior versus simply targeting the Bilibili platform, this can present a natural-language locale policy concern.

Natural-Language Policy Violations

Low

• Confidence: 91% confidence
• Finding: The comments and all user-facing output strings are in Chinese, which effectively forces a specific language for users of the skill. The file does not indicate that this is a China-specific or Chinese-only tool, nor does it provide any opt-in or alternative language handling.