Security audit

TransPrompt｜一句指令，把需求变成可直接发给 AI 的专业 Prompt

Security checks for vulnerabilities and agentic risk

Overview

This Markdown-only skill turns @prt/@prompt messages into reusable AI prompts and does not request system access, though some labels and examples are Chinese.

Install this if you want a lightweight prompt-conversion shortcut. Review generated prompts before copying them into other AI tools, and expect that some default section labels may appear in Chinese unless the agent adapts them to your language.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (7)

Natural-Language Policy Violations

Medium

Confidence: 97% confidence
Finding: The documented standard and assumptions-based output formats require fixed Chinese phrases such as “您的专属 Prompt 已生成，请审查：” and “Prompt 关键处理,” which imposes a specific language on user-facing responses. This conflicts with the policy requirement to avoid forcing a language or locale unless the user is given a choice or the constraint is explicitly justified.

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: SQP-3 applies to all file types and covers language or locale policy violations. This document consistently presents trigger examples, recovery text, and interaction guidance only in Chinese, which can effectively force a specific language/locale without user opt-in or documented justification.

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: The file's user inputs, preferred replies, and suggested wording consistently require Chinese responses such as '请输入您要转化的需求' and Chinese example prompts. This indicates a language policy constraint in natural-language instructions without any opt-in, alternative language path, or justification that the skill is region-specific.

Natural-Language Policy Violations

Medium

Confidence: 97% confidence
Finding: The example prompt explicitly instructs the assistant in Chinese, which imposes a language choice rather than leaving language aligned to user preference. The same pattern appears across multiple example blocks, making this a natural-language locale policy concern rather than a one-off wording issue.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: This example defines the assistant role and output structure entirely in Chinese, which can steer users toward a fixed language/locale. Because the document does not indicate that language should be chosen by the user, it violates the requirement to avoid forcing a specific language without opt-in.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The full example prompt is written as a Chinese instruction set and does not offer an alternative based on user preference. There is no documented reason that this skill must operate in Chinese, so the fixed-language example creates a policy issue.

Natural-Language Policy Violations

Low

Confidence: 91% confidence
Finding: The guide includes a Chinese trigger example and later specifies an output element named `Prompt 关键处理`, which suggests the skill may produce mixed-language output by default. Because the document does not state that language follows user preference or that multilingual behavior is optional, this can violate language/locale policy expectations.

Static analysis

No suspicious patterns detected.