Security audit

Openapi Docs Generator

Security checks across malware telemetry and agentic risk

Overview

This is a documentation workflow skill for OpenAPI and Swagger tasks, with no executable code, install hooks, persistence, credential handling, or data-exfiltration behavior found.

Installers should expect a low-risk OpenAPI documentation helper. Use it for explicit OpenAPI, Swagger, REST endpoint documentation, schema validation, or API-doc review tasks; be aware it may be selected too broadly for generic API or developer-experience requests.

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 (9)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger phrases are extremely generic and can cause the skill to activate in situations that only loosely match the intended OpenAPI documentation use case. Over-broad activation increases the chance of inappropriate skill selection, which can override more suitable instructions, expose irrelevant workflows, or be abused for prompt-routing manipulation in multi-skill environments.

Vague Triggers

High

Confidence: 94% confidence
Finding: The trigger phrases are broad enough to match ordinary user requests about APIs, Swagger, or documentation, which can cause the skill to activate outside its intended scope. Over-broad activation increases the chance of prompt-routing mistakes, accidental disclosure of irrelevant internal instructions, or unreviewed behavior being applied in contexts the user did not intend.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The skill description and activation scope are broad enough that the skill may trigger for loosely related requests, causing the agent to route users into this skill when a more appropriate or safer skill should handle the task. Overbroad routing increases the chance of unintended authority, irrelevant instructions, or data exposure through unnecessary processing of user inputs.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The example trigger phrases are malformed and overly generic, which can cause incorrect skill invocation based on everyday language rather than clear user intent. This weakens routing precision and may lead to accidental execution of the skill in contexts where it is irrelevant, reducing reliability and potentially exposing user content to an unnecessary processing path.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The skill description and usage criteria are broad enough that it could trigger on ordinary discussions involving software, APIs, or documentation, even when the user did not intend to invoke a specialized workflow. Over-triggering can cause inappropriate routing, irrelevant instructions, or unintended disclosure/use of contextual data meant for a narrower task.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger keyword list includes generic terms like 'software-and-data' and 'developer experience' that overlap heavily with normal technical conversation. This increases the chance of accidental activation, which can misroute user requests and apply the wrong task-specific behavior in unrelated contexts.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The default prompt uses very broad, natural-language phrasing about helping with backend/platform needs and OpenAPI documentation, which can overlap with ordinary user requests and increase the chance of unintended or implicit invocation. Because implicit invocation is enabled, this broad trigger surface can cause the skill to activate in contexts the user did not clearly intend, expanding access to the skill and any downstream behaviors.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger sentence is overly broad and malformed, increasing the chance that the skill activates on ordinary user phrasing rather than a clearly scoped request. In an agent environment, this can cause unintended routing to this skill, which may override more appropriate tooling or inject irrelevant workflow steps into unrelated conversations.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The activation examples are malformed, truncated, and do not clearly define what user intent should activate the skill. Poorly specified activation patterns can lead to false positives in skill selection, causing the agent to invoke this skill in contexts only loosely related to the requirement and reducing reliability or enabling prompt-routing abuse.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.