Security audit

Openapi Docs Generator

Security checks across malware telemetry and agentic risk

Overview

This skill is a documentation helper for OpenAPI/Swagger work and does not contain hidden code, persistence, credential handling, or destructive behavior.

Install this if you want an agent to help with OpenAPI, Swagger, REST API documentation, validation plans, or related checklists. Be aware it may be selected automatically for broad API documentation wording, so use explicit requests when you want this skill and choose another tool for unrelated API debugging or architecture work.

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: 90% confidence
Finding: The trigger examples are written as natural-language everyday phrases that are broad enough to match ordinary user requests, which can cause the skill to activate outside a clear user opt-in. In an agent environment, overbroad invocation increases the chance of unintended context capture, unnecessary instruction injection, or routing a benign request into a more privileged workflow than the user expected.

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The trigger phrases are broad and partly templated in a way that could cause the skill to activate for loosely related requests, especially around common terms like OpenAPI, Swagger, or practical workflow help. Unintended invocation can route user requests into the wrong skill, causing incorrect handling, disclosure of unnecessary context to the skill, or bypass of more appropriate controls.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The skill description and trigger scope are broad enough to match many API- or software-related requests without strong boundaries, which can cause inappropriate auto-selection of this skill outside its intended niche. Overbroad routing is dangerous because it increases the chance the agent applies domain-specific instructions or workflows in contexts where they are irrelevant, potentially degrading responses or bypassing more appropriate safeguards from other skills.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger examples use generic phrasing like 'Help me' and 'I need a practical workflow' with only loosely attached requirement text, making the skill easier to invoke from ambiguous natural-language requests. This is risky because generic trigger examples can bias routing systems toward activating the skill on ordinary requests that lack a clear OpenAPI documentation intent, leading to mis-scoping and unreliable behavior.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The skill description and activation guidance are broad enough that normal API-related conversations may unintentionally trigger this skill outside its intended scope. Over-broad activation can cause inappropriate context switching, irrelevant instructions, or unintended handling of user inputs, which is a genuine security and safety concern in agent routing even without overtly malicious content.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The keyword list includes common terms like 'openapi', 'swagger', 'rest api', and 'developer experience' without boundary conditions, which increases the chance of accidental invocation during unrelated technical discussions. In an agent system, this can lead to misrouting, over-collection of context, or the model applying the wrong workflow to user requests, making the issue operationally and potentially security relevant.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The skill enables implicit invocation without any visible activation constraints, narrowing rules, or user-confirmation guardrails. That can cause the agent to auto-select this skill in broader contexts than intended, increasing the risk of prompt-scope overreach, unintended disclosure of user data to the skill context, or unreviewed actions based on loosely matched requests.

Vague Triggers

High

Confidence: 94% confidence
Finding: The trigger sentence is excessively broad and malformed enough that it could match ordinary user phrasing rather than a clearly intentional tool invocation. That increases the chance the skill activates in contexts where the user did not explicitly request it, causing prompt hijacking of unrelated conversations or unintended handling of sensitive API/documentation content.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The invocation guidance is underspecified and does not define precise boundaries for when the skill should or should not run. In an agentic environment, vague trigger rules can cause over-selection of this skill, leading to unintended context capture, user confusion, or interference with more appropriate skills.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.