Security audit

Ai News Zh

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese AI news collection and delivery workflow with no executable code or hidden local access.

Install only if you want an agent to fetch public AI news from external sites, translate it into Chinese, and optionally send it to configured Feishu, Telegram, or Discord destinations. Review the channel and cron settings before enabling scheduled delivery.

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 (4)

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill advertises scheduled automatic pushing to Feishu, Telegram, and Discord, but does not clearly warn that content will be transmitted to external third-party channels. This can cause users or operators to enable automated outbound data flow without fully understanding that fetched, translated, or possibly mis-scoped content will be sent outside the local environment on a recurring basis.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The manual trigger phrase is a normal conversational request ('帮我采集今天的AI新闻，整理成中文日报') that can easily overlap with ordinary user intent. In agents that auto-route based on matching phrases, this broad trigger increases the chance of unintended skill activation, leading to unreviewed web fetching and possible downstream outbound publishing behavior.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: The formatting rule explicitly states that headlines must be in Chinese, and the template content is entirely Chinese-formatted. This is a natural-language locale constraint that does not offer the user any language choice or document an opt-in, which can violate language/locale policy requirements.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The note specifies a mandatory translation behavior to Chinese for all sourced content. This is a natural-language locale policy constraint presented without indicating user choice, opt-in, or a justified region-specific limitation.

Static analysis

No suspicious patterns detected.