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 activation wording is broader than ideal.

This skill appears safe to install for OpenAPI/Swagger documentation assistance. Be aware that it may activate for general API or documentation requests because its trigger wording is broad; if that happens, invoke a more specific skill or ask the agent not to use this one for unrelated backend 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 (10)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger guidance is broadly phrased and tied to a wide requirement statement rather than a narrowly scoped user intent, which can cause the skill to activate for loosely related API or documentation requests. In an agent system, overbroad activation can misroute conversations, override more appropriate skills, or expose users to unintended instruction sets, even without explicit malicious content.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The phrases 'Help me ...' and 'I need a practical workflow ...' begin with extremely common conversational language, making them likely to match ordinary requests that were not intended to invoke this specific skill. This increases the risk of accidental activation and prompt-routing errors, especially in multi-skill environments where many tasks start with similar wording.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger phrases are generic and structurally broad, making accidental or overly eager invocation of the skill more likely when a user mentions OpenAPI, Swagger, or practical help in passing. In an agent ecosystem, this can cause inappropriate routing, unexpected disclosure of context to the skill, or execution of an irrelevant workflow without clear user intent.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The skill description and invocation criteria are broad enough that the skill may be selected for loosely related software or API questions, not just OpenAPI/Swagger documentation tasks. Over-broad routing can cause unintended activation, which increases the chance of irrelevant guidance, prompt-scope confusion, or interception of requests meant for a more appropriate skill.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The example trigger phrases use generic wording such as 'Help me' and 'I need a practical workflow' combined with a truncated requirement statement, which does not strongly constrain invocation to OpenAPI documentation contexts. In a skill-routing system, such vague examples can increase accidental matches and lead to misrouting or over-selection of this skill.

Vague Triggers

Medium

Confidence: 84% confidence
Finding: The skill description and usage scope are broad enough that ordinary conversations about software, APIs, or documentation could trigger it unintentionally. While this is not a code-execution flaw, over-broad activation can cause the wrong skill to engage, leading to irrelevant guidance, context confusion, or unintended processing of user inputs.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The keyword list contains common technical terms such as 'openapi', 'swagger', 'api documentation', and 'rest api' without scoping rules or disambiguation. In an agent environment, this raises the chance of accidental invocation during routine engineering chats, which can misroute requests, override more suitable skills, or expose unnecessary context to this skill.

Vague Triggers

Medium

Confidence: 83% confidence
Finding: The default prompt is broad and generic enough that it could be invoked for common API or software-help requests beyond a narrowly intended scope. With implicit invocation enabled, this increases the chance of accidental routing to the skill when a user did not explicitly ask for it, which can create prompt-scope confusion and unintended handling of requests.

Vague Triggers

High

Confidence: 96% confidence
Finding: The trigger sentence begins with a generic everyday phrase ('Help me') and then appends broad requirement text, making accidental activation much more likely in normal conversation. In an agent-routing system, this can cause the skill to run when the user did not explicitly request OpenAPI documentation help, potentially leading to misrouting, prompt-context pollution, or unintended handling of unrelated requests.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The sentence 'I need a practical workflow for ...' is still too ambiguous because 'practical workflow' is broadly applicable across many tasks and does not by itself uniquely indicate an OpenAPI/Swagger documentation need. This increases the chance of unintended invocation for unrelated planning or implementation requests, especially in systems that match loosely on trigger text.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal