Security audit

Tweet Thread Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple tweet-thread template generator with no evidence of hidden access, persistence, exfiltration, or destructive behavior, though it overstates its actual generation features.

Install only if you are comfortable with a placeholder/demo-style formatter rather than a real article converter. Review output before posting anything publicly, because it does not actually summarize your source material or generate real hashtags from content.

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

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 98% confidence
Finding: 声明描述的是一个可将技术文章或博客内容转换为 Twitter/X 线程的工具，且支持多语言、自动添加话题标签。实际代码中虽然接受 text|url|file 等来源参数和若干选项，但没有任何读取文件、获取 URL、解析文章、总结内容或基于输入生成推文的逻辑。输出内容是固定的 here-doc 模板，包含 TOPIC_PLACEHOLDER、CONTENT_PLACEHOLDER 等占位符以及固定建议。它的表面主题与声明相关，但核心能力并未实现，因此描述与实际行为存在实质性不符。

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: The manifest description is written as a directive to convert technical articles into Twitter/X threads in Chinese, with no indication that users can choose another language or opt in to this locale constraint. That creates a natural-language locale policy concern because the skill appears to impose a specific language by default.

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: Lines L116-L120 present engagement tips in Chinese as part of the generated output, which forces a specific language for user-facing content. The file does not provide an opt-in, fallback, or justification for this locale choice, so it conflicts with the language/locale policy requirement.

Natural-Language Policy Violations

Low

Confidence: 77% confidence
Finding: The file is primarily written in Chinese, but the options table sets `--lang` to `en` by default. This creates a locale expectation mismatch and may force English output unless the user explicitly overrides it, without documenting why English is the default or asking for user preference.

Static analysis

No suspicious patterns detected.