Security audit

Openapi Docs Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation workflow skill for OpenAPI/Swagger work; its main issue is overly broad activation wording, not malicious behavior.

Installers should expect a lightweight OpenAPI/Swagger documentation assistant. Review or narrow the activation phrases if your environment relies on implicit skill routing, because the current wording may activate on broad API or developer-experience prompts.

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 (13)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger sentences are broad natural-language phrases that can match ordinary user requests and cause the skill to activate when the user did not explicitly intend to invoke it. In an agentic system, unintended activation can redirect task flow, inject irrelevant instructions, or crowd out more appropriate skills, making this a genuine prompt-routing weakness even though it is not a code-execution issue.
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 and generic enough that the skill may activate for loosely related requests, causing unintended routing or overshadowing more appropriate skills. In an agent environment, ambiguous invocation expands the skill’s effective scope and can lead to incorrect task handling, including accidental use on requests the user did not clearly intend for this skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill description and frontmatter usage guidance are broad enough to match common API-related requests without strong boundaries, which can cause unintended invocation. Over-broad routing can expose users to irrelevant or lower-quality skill behavior, and in a multi-skill environment it may override more appropriate or safer specialized skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The trigger keywords include generic terms such as 'software-and-data' and broad developer-experience language that are likely to match many unrelated prompts. This increases the chance of accidental activation, misrouting, and prompt-surface expansion, especially when multiple skills compete for selection.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: L04 将技能适用条件表述为“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，且未说明排除条件，容易与普通 API/文档求助场景重叠，造成不必要调用。
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The keyword triggers include very common terms such as 'software-and-data', 'openapi', and 'rest api' without scope limits or exclusion rules. This can cause the skill to activate on loosely related prompts, leading to prompt-routing confusion, inappropriate application of the workflow, and possible leakage of irrelevant instructions into other tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The default prompt is overly broad and grammatically loose, containing generic phrases like 'help me' and a long natural-language description that can match many unrelated backend or API-documentation requests. Combined with implicit invocation, this increases the chance the skill is auto-selected when the user did not clearly intend to use it, which can cause prompt routing errors, unexpected behavior, or exposure of the skill in inappropriate contexts.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger sentence is so broad and malformed that it could match ordinary user phrasing about needing help, causing the skill to activate outside its intended scope. Overbroad activation can route unrelated conversations into this skill, leading to inappropriate instructions, context capture, or interference with safer/more relevant skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This activation phrase is ambiguous because it tells the system to 'use' the skill for a very long, generic requirement statement rather than a concrete, bounded user intent. Such ambiguity increases accidental or adversarial invocation risk, allowing the skill to be triggered in contexts where it does not belong and potentially bypassing better-scoped routing.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 75% confidence
Finding: The evidence section includes Chinese-language titles and links in an otherwise English README, but the document does not explain the language behavior or offer user opt-in for locale preferences. This can create a language/locale policy concern because the skill's user-facing materials implicitly mix languages without documented choice or justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This file is labeled as a Chinese README, but substantial user-facing content including the demand description, workflow summary, keywords, and trigger phrases is presented in English. That creates an implicit language constraint/mismatch without documenting a language choice or opt-in for users.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The example trigger sentences are malformed and truncate the requirement text, so they do not provide reliable guidance for safe or precise invocation. Poor trigger examples can lead to ambiguous matching behavior and make it harder to constrain the skill to its intended documentation use case.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: 该文件为 SKILL.zh-CN.md，内容整体以中文呈现，但未见向用户提供语言选择、切换机制或说明该语言限制的适用范围。按照语言/locale 政策，若技能隐含强制特定语言而无用户选择，属于自然语言策略风险。
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.