ClawHub
Back to skill

Security audit

Openapi Docs Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation workflow skill for OpenAPI/Swagger work, with no executable code or hidden data access, though its activation wording is broader than ideal.

Safe to install for OpenAPI/Swagger documentation assistance. Be aware it may activate on broad API or developer-experience prompts, so prefer explicit invocation when you want it and ignore or disable implicit routing if your environment supports that.

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

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger sentences are generic and template-like, so they can match ordinary user requests that merely mention OpenAPI or practical workflow help, causing the skill to activate when the user did not explicitly intend it. In an agent environment, unintended invocation can steer responses, override more appropriate skills, or expose the system to prompt-surface expansion through unnecessary skill loading.

Content

No source excerpt is available for this finding.

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger sentence is so generic that it can match ordinary user requests and cause the skill to activate outside its intended scope. Overbroad activation increases the chance of unintended routing, prompt interference, and misuse of the skill in contexts where its assumptions or safeguards do not apply.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger phrases are broad and partially generic, including natural-language prompts like 'Help me' and 'I need a practical workflow' combined with a long requirement sentence. This increases the chance the skill is invoked in contexts where the user did not specifically intend to call this skill, which can misroute requests or cause inappropriate automation in multi-skill environments.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description and activation guidance are broad enough to match many generic software or API-related requests, which can cause the agent to invoke this skill outside its intended scope. Over-broad routing is dangerous because it can override a more appropriate skill, produce irrelevant or misleading output, and widen the attack surface for prompt-routing abuse.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The keyword list contains broad phrases like 'software-and-data', 'openapi', 'swagger', and 'developer experience' without sufficient scope constraints, making accidental or adversarial triggering more likely. This is risky because a malicious or noisy prompt can intentionally include these generic terms to force selection of this skill even when the user’s real task is unrelated.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

技能描述将适用范围定义得过宽：只要用户提到 openapi、swagger、api documentation、rest api 或需要某类“支持”就可能调用该技能，但没有清晰的边界或不适用场景。这样的设计会扩大攻击面和误路由概率，使代理在普通软件咨询、API 设计讨论甚至无关文档任务中错误启用该技能。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

触发关键词包含较宽泛的术语，如 software-and-data、openapi、swagger、rest api、developer experience，容易与大量普通技术对话重叠，导致技能在不需要时被调用。误触发会让代理偏离用户真实意图，增加错误指导、上下文污染或把后续敏感内容交给不相关技能处理的风险。

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill enables implicit invocation while using a very broad default prompt trigger that matches common API and software-documentation requests. This can cause the agent to invoke the skill in situations the user did not explicitly authorize, increasing the chance of unintended prompt injection exposure, over-broad data handling, or incorrect tool use in unrelated contexts.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

A vague invocation description can cause the orchestrator to select this skill for loosely related requests, which may override more appropriate tools or produce irrelevant outputs. In agent systems, ambiguous routing logic is a security and reliability issue because it widens the attack surface for prompt-trigger abuse and accidental execution.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This file is labeled as a Chinese README, but important descriptive and invocation text is presented in English, including the main requirement statement and trigger phrases. In a locale-specific documentation file, that can violate language policy expectations when no language choice or rationale is provided.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

示例触发句非常泛化，几乎只是重复需求描述，且没有展示边界案例或负例，无法帮助路由系统准确区分何时应触发该技能。结果是模型更容易把模糊相似请求错误归入该技能，降低选择精度并放大前述误触发问题。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.