Security audit

Openapi Docs Generator

Security checks across malware telemetry and agentic risk

Overview

This is a documentation helper for OpenAPI/Swagger work, with broad trigger wording but no hidden execution, credential use, persistence, or destructive behavior.

Installers should be aware that this skill may activate for broad API or developer-experience wording. It is otherwise a low-risk documentation workflow skill; use explicit OpenAPI/Swagger documentation requests to keep invocation precise.

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 generic and awkwardly templated, which increases the chance the skill is invoked when a user's request only loosely matches the topic. In an agent environment, unintended invocation can route user data or task flow into the wrong skill, causing incorrect actions, misleading outputs, or unnecessary exposure of contextual information to skill logic.

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The trigger phrases are broad and partially malformed, matching generic requests about OpenAPI, Swagger, API documentation, or practical workflows. This increases the chance the skill is invoked unintentionally in contexts the user did not explicitly target, which can cause incorrect routing, over-collection of context, or interference with safer/more appropriate skills.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The skill description and usage conditions are broad enough to match many common software requests beyond narrowly scoped OpenAPI documentation tasks. This can cause the skill to be invoked in inappropriate contexts, increasing the chance of irrelevant guidance, prompt collisions with more appropriate skills, or accidental handling of requests outside its validated capability boundary.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The example trigger phrases use very generic wording such as 'Help me' and 'I need a practical workflow,' which are common across many unrelated tasks. Because trigger examples often shape routing behavior, this weak specificity can lead to over-activation of the skill and misclassification of user intent, reducing safety and reliability of skill selection.

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The skill description uses broad trigger terms such as 'software-and-data', 'openapi', 'swagger', 'api documentation', and 'rest api' without enough narrowing conditions. This can cause the skill to activate in ordinary technical conversations where the user did not intend to invoke documentation-generation behavior, increasing the chance of irrelevant guidance, context hijacking, or unintended workflow execution.

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The keyword list contains very common technical phrases, including 'rest api' and 'developer experience', that appear in many unrelated engineering discussions. Overbroad keyword matching raises the likelihood of accidental invocation, which may steer the agent away from the user’s actual goal or expose internal skill behavior in contexts where it is not appropriate.

Vague Triggers

Low

Confidence: 89% confidence
Finding: The example trigger sentences begin with highly reusable phrases like 'Help me' and 'I need a practical workflow for', which are common across normal assistant interactions. These examples reinforce ambiguous activation patterns and may encourage implementations that match on generic phrasing rather than the specialized OpenAPI-documentation intent.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The skill enables implicit invocation without defining narrow trigger constraints, which can cause the agent to invoke this skill in situations broader than the user intended. That increases the risk of prompt-scope confusion, unintended handling of API specs or internal documentation, and abuse through crafted user inputs that steer automatic tool selection.

Vague Triggers

High

Confidence: 93% confidence
Finding: The trigger sentences are templated so broadly that ordinary user requests about backend help or practical workflows could unintentionally invoke this skill outside a clearly bounded OpenAPI/Swagger context. Over-broad activation increases the chance of incorrect routing, context confusion, and accidental exposure of this skill's behavior in unrelated conversations.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.