Security audit

Openapi Docs Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-assistance skill for OpenAPI/Swagger work with no executable code, persistence, credential handling, or hidden data movement.

This skill appears safe to install for OpenAPI and Swagger documentation work. Be aware that its activation phrases are loose, so it may be invoked for some general API or developer-experience requests where a more specific skill would be better.

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 (11)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger sentences are generic enough that normal user requests about APIs, documentation, or workflows could invoke this skill unintentionally. In an agent system with multiple skills, this can cause misrouting, unexpected prompt/context injection, and execution of capabilities the user did not explicitly request, which increases the attack surface even if the skill itself is not overtly dangerous.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger phrases are broad, templated, and partially malformed, which increases the chance that ordinary user requests about OpenAPI, Swagger, or API docs will invoke the skill unintentionally. In an agent environment, overbroad activation can route unrelated conversations into this skill, causing incorrect handling, context bleed, or misuse of downstream capabilities.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill description is broad enough to match many ordinary software requests beyond narrowly scoped OpenAPI documentation work. Overly broad routing can cause the agent to invoke this skill in unintended contexts, leading to irrelevant guidance, prompt-scope confusion, or accidental exposure of user context to a skill that was not the best match.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger keywords include generic terms such as 'software-and-data' and broad API-related phrases that are likely to collide with common developer requests. This increases the chance of false-positive activation, which can misroute conversations, override more appropriate specialized skills, and degrade security boundaries based on correct skill selection.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 83% confidence
Finding: 整个技能文档以 zh-CN 形式呈现，且未说明这是可选语言版本、未提示可切换语言，也未提供用户语言偏好选择。按规则，这类默认强制特定语言而无用户 opt-in 的自然语言约束属于 locale policy 风险。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: L04 写明“当用户提出 software-and-data, openapi, swagger, api documentation, rest api，或需要围绕该需求获得实用流程、产物、检查清单、分析或实现支持时使用”，其中“需要围绕该需求获得实用流程、产物、检查清单、分析或实现支持”范围非常宽，未说明何时应触发或不应触发。该描述缺少明确约束和排除条件，容易与一般性求助请求重叠。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: L48-L49 的示例以“Help me”和“I need a practical workflow for”开头，这类表达与日常通用求助语句高度重叠；后续拼接的需求描述也未形成清晰、可复用的精确触发模式。缺少具体限定会增加技能在普通对话中被误调用的风险。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt is framed as a broad natural-language trigger ('Use $openapi-docs-generator to help me ...') rather than a narrowly scoped invocation condition, which can cause the skill to activate in loosely related conversations. Because the skill is configured with implicit invocation, this increases the chance of unintended routing or prompt injection exposure through ordinary discussion of APIs or documentation topics.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger examples include highly generic phrasing such as 'Help me' and 'I need a practical workflow', which can match ordinary user requests far beyond OpenAPI documentation. That can cause unintended skill activation and steer unrelated conversations into this skill's workflow, creating routing confusion and possible prompt-scope abuse if the agent prioritizes matched triggers over actual user intent.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 71% confidence
Finding: This is a Chinese README, but several key user-facing sections, including the demand description, workflow description, keywords, and trigger phrases, are presented in English with no statement about language preference. That can impose a locale/language experience on users without explicit opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The file heavily mixes Chinese-language evidence and trigger context without stating whether the skill supports multiple languages or allows user choice. Because natural-language examples and sourcing are skewed toward a specific locale, the skill documentation should clarify language behavior to avoid implying a fixed language preference.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.