Security audit

Openapi Docs Generator

Security checks across malware telemetry and agentic risk

Overview

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

Before installing, be aware that this skill may be invoked for some general REST API or developer-experience prompts. It appears safe for OpenAPI/Swagger documentation tasks, but users should choose a more specific skill when they need general backend design, implementation, or unrelated API help.

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: 92% confidence
Finding: The trigger phrases are broad, templated, and partially malformed, which increases the chance the skill is invoked for loosely related requests rather than explicit user intent. In an agent environment, unintended invocation can route user data or workflow control to the wrong skill, causing incorrect outputs, prompt-surface expansion, and downstream security or privacy issues.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The listed trigger phrases are broad and partly templated in a way that could match generic user requests about backend help, workflows, or API documentation rather than a clear request to invoke this specific skill. That increases the risk of unintended activation, which can cause the agent to run the wrong skill, bypass better-matched tools, or expose users to outputs they did not explicitly request.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The skill description and trigger criteria are broad enough to activate on common API-related requests that may not specifically require OpenAPI documentation support. This can cause inappropriate skill routing, leading the agent to apply the wrong workflow, reduce response quality, or expose users to irrelevant automated guidance in contexts outside the skill’s intended scope.

Vague Triggers

Medium

Confidence: 80% confidence
Finding: The example trigger phrases are generic enough that routine help requests could invoke this skill even when the user is not actually asking for OpenAPI or Swagger documentation work. Overbroad trigger examples increase the chance of misrouting and make prompt selection less precise, which is a security-relevant quality issue in agentic systems.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger description in the frontmatter is broad and overlaps with common developer-assistance requests such as OpenAPI, Swagger, API documentation, and REST API work. This can cause the skill to activate for loosely related prompts, leading to unintended routing, over-collection of context, or the application of an irrelevant workflow, though it does not directly enable code execution or data exfiltration.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The example trigger phrases begin with very generic language like 'Help me' and 'I need a practical workflow', which can match ordinary conversation patterns when combined with broad domain terms. In practice this increases accidental invocation risk and may bias orchestration toward this skill even when a more appropriate skill or direct response should be used.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The skill description and default prompt use very broad activation terms like software-and-data, openapi, swagger, api documentation, rest api, and generic requests for workflows or analysis. This can cause the agent to invoke the skill in contexts beyond narrowly intended OpenAPI documentation tasks, increasing the chance of prompt hijacking, irrelevant tool use, or unreviewed handling of unrelated user content.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger sentence is extremely broad and closely resembles ordinary user language, which can cause the skill to activate for loosely related requests instead of explicit OpenAPI/Swagger documentation tasks. In an agent system, this increases the chance of unintended routing, where the wrong skill handles user input and may produce irrelevant or misleading outputs that bypass more appropriate controls.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: This trigger lacks clear scope and actionable boundaries, so it can match a wide range of vague requests without confirming that the user actually wants OpenAPI or Swagger documentation assistance. Ambiguous activation criteria are dangerous because they expand the skill's effective authority and make prompt routing easier to manipulate or accidentally invoke.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.