Security audit

@prompt v1.0正式版

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill rewrites prefixed user requests into copy-ready prompts and does not add execution, persistence, credentials, or data access behavior.

Installers should expect a lightweight prompt-writing helper. The main thing to consider is language fit: some response labels and examples default to Chinese, so non-Chinese users may want the author to clarify or localize the output contract.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (9)

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: The required standard output templates are written in Chinese and presented as the default contract, while the skill otherwise says to preserve the user's language unless they ask otherwise. This creates a natural-language policy issue because it imposes a specific language on user-facing responses without opt-in or a documented region-specific constraint.

Natural-Language Policy Violations

Medium

Confidence: 88% confidence
Finding: The examples and invocation patterns are presented exclusively in Chinese, including user-facing trigger examples and suggested responses. Because the guide does not state that this is a China-specific or Chinese-only skill, this reads as a language policy constraint without user opt-in.

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: This markdown file repeatedly presents inputs, preferred replies, and suggested wording exclusively in Chinese, including user-facing response templates. Because the guidance does not offer a language choice or explain a region-specific constraint, it implicitly enforces a specific language/locale policy.

Natural-Language Policy Violations

Medium

Confidence: 86% confidence
Finding: The title labels this as an "English Guide," which indicates a language constraint in the skill documentation. Under the policy, forcing or defaulting to a specific language without user opt-in can be a natural-language policy violation unless the locale limitation is clearly justified or alternatives are offered.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The example prompt explicitly instructs the assistant in Chinese, which effectively sets a language expectation without user opt-in. This file contains multiple such examples, and no surrounding text explains that language should be selected based on user preference or context.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The example prompt explicitly instructs the assistant in Chinese, which effectively sets a language expectation without user opt-in. This file contains multiple such examples, and no surrounding text explains that language should be selected based on user preference or context.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The example prompt explicitly instructs the assistant in Chinese, which effectively sets a language expectation without user opt-in. This file contains multiple such examples, and no surrounding text explains that language should be selected based on user preference or context.

Natural-Language Policy Violations

Low

Confidence: 87% confidence
Finding: Line L14 states the output was changed to a shorter `Prompt 关键处理` summary, which implies a specific language choice in user-facing output. The file does not indicate that users can opt into this language or that the skill is intentionally scoped to Chinese-language usage.

Natural-Language Policy Violations

Low

Confidence: 93% confidence
Finding: The heading explicitly labels this as a Chinese-language guide, and the rest of the file is entirely in Chinese. Under the policy for natural-language violations, forcing a specific language without offering user choice or documenting a justified locale constraint can be a violation.

Static analysis

No suspicious patterns detected.