Security audit

Openapi Docs Generator

Security checks across malware telemetry and agentic risk

Overview

This skill is a documentation workflow helper for OpenAPI/Swagger tasks, with no hidden execution, credential access, persistence, or destructive behavior found.

Install this if you want a general OpenAPI/Swagger documentation assistant. Be aware that its broad triggers may make it appear in adjacent API or developer-experience conversations, so explicitly choose a different skill when the task is not about API documentation generation, validation, or improvement.

SkillSpector

By NVIDIA

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 (10)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger sentences are generic and malformed enough that they could match loosely related requests and cause the skill to activate unintentionally. In an agent system, over-broad invocation increases the risk of the skill being selected in the wrong context, which can lead to irrelevant actions, context leakage across tasks, or unsafe downstream guidance being produced without clear user intent.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The trigger phrases are broad, repetitive, and partially templated, which increases the chance the skill is invoked when a user did not explicitly intend to use it. In an agent environment, unintended invocation can route user requests into the wrong workflow, causing incorrect documentation generation, context leakage across tasks, or unnecessary tool use.

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The skill description is broadly scoped around common API-documentation terms and general implementation support, which can cause the agent to invoke this skill for a wide range of loosely related requests. Over-broad routing increases the chance of unintended activation, context confusion, and inappropriate guidance being applied outside the intended OpenAPI documentation use case.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger keywords include generic terms such as 'software-and-data' and 'developer experience' without guardrails, making accidental or inappropriate invocation likely. In an agent system, ambiguous triggers can misroute user requests, causing irrelevant instructions to be applied and potentially interfering with safer or better-matched skills.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The trigger keywords are broad and include generic terms like "software-and-data", "openapi", "swagger", and "rest api" without clear exclusion boundaries. This can cause the skill to activate in conversations that merely mention these topics, leading to inappropriate routing, context hijacking, or overshadowing of more relevant skills.

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The skill description defines usage in very general terms and does not clearly separate in-scope requests from adjacent but unrelated software or API discussions. In a skill-routing system, ambiguous activation criteria can produce unintended invocation, reducing reliability and potentially exposing the user to irrelevant transformations or outputs.

Vague Triggers

Low

Confidence: 78% confidence
Finding: The example trigger phrases use generic help-seeking language such as "Help me" and "I need a practical workflow," which overlaps heavily with normal conversation patterns. Even though the examples mention OpenAPI documentation, this style increases accidental matching risk and can bias routers toward this skill in borderline cases.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The default prompt uses very broad natural-language trigger wording around common concepts like OpenAPI, Swagger, API documentation, and REST APIs, which can cause the skill to be invoked in ordinary conversations that only loosely relate to documentation generation. Because implicit invocation is enabled, this increases the chance of unintended activation, exposing users to unexpected behavior, prompt injection surface, or context leakage into a skill they did not explicitly request.

Vague Triggers

High

Confidence: 90% confidence
Finding: The trigger examples are broad enough to match ordinary user phrasing about APIs and documentation, which can cause the skill to activate outside its intended scope. Over-broad activation is dangerous because it can route unrelated requests into this skill, increasing the chance of incorrect handling, prompt interference, or unintended disclosure of contextual data to the skill.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The invocation examples lack precise boundaries and do not clearly constrain when the skill should be selected, making accidental or overly permissive routing more likely. In an agent environment, ambiguous routing can expose users to the wrong workflow, degrade reliability, and create opportunities for prompt-trigger abuse through crafted user phrasing.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.