Security audit

内容爆款拆解师

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language content-analysis workflow that fetches user-provided links and can optionally share generated output to Feishu.

Install only if you want a Chinese-language workflow for analyzing and rewriting content from supplied links. Do not give it confidential links or private Feishu documents unless you are comfortable with the agent fetching their contents and, when Feishu output is requested or used in a Feishu context, sending generated material through Feishu tools.

A.I.G

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

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger phrases are broad enough to match common user requests such as '分析这条链接' or '帮我分析这个视频/笔记', which can cause the skill to activate unintentionally in conversations that did not clearly request this specific workflow. Because the skill then fetches arbitrary links and generates downstream content automatically, accidental activation can lead to unexpected external requests, content processing, or data handling beyond user intent.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill is designed to fetch arbitrary URLs and optionally push generated output to Feishu, but it does not present any warning, consent step, or validation around privacy-sensitive content and external data transmission. In practice, this can expose private documents, internal pages, tokenized links, or sensitive scraped content to third-party services or unintended recipients if the user supplies a confidential URL or enables Feishu push.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The skill specification is entirely Chinese and sets a default output style of 公众号风格 when the user does not specify otherwise. There is no indication that users may opt into another language or locale, which can violate language/locale policy when the skill is used in broader contexts.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The document uses Chinese throughout, beginning with the title at L01 and continuing for the full file. Under the language/locale policy, forcing a specific language without user opt-in or a documented justification is a natural-language policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The file title and all instructions are written in Chinese and the templates are specifically for Chinese platforms such as 公众号 and 小红书. It also uses hard requirements such as Chinese title lengths and emoji usage, but nowhere indicates that this locale is optional or limited to a region-specific skill, which can violate language/locale policy expectations.
Content: No source excerpt is available for this finding.