Security audit

Openapi Docs Generator

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-workflow skill for OpenAPI/Swagger work, with broad routing wording but no code execution, persistence, credential use, or hidden data handling.

Install this if you want help with OpenAPI or Swagger documentation workflows. Be aware that its broad trigger metadata could make it activate on some general API-documentation conversations, so explicitly name another skill or clarify intent if it is selected when you do not want it.

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: 83% confidence
Finding: The trigger sentences are broad and generic enough that the skill may activate in contexts beyond narrowly scoped OpenAPI documentation help. Overbroad activation can cause unintended invocation, context hijacking, or the application of specialized instructions when the user did not clearly request this skill, which is a real security and safety concern in agent routing.

Vague Triggers

High

Confidence: 94% confidence
Finding: The trigger phrases are extremely broad and include generic wording like 'Help me' and 'I need a practical workflow', which can cause accidental or overly eager invocation outside the user's actual intent. In an agent system, ambiguous triggers increase the chance that the skill activates on unrelated requests and influences outputs in contexts the user did not explicitly select.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The skill description and usage guidance are broad enough to match many ordinary API, Swagger, or REST-documentation requests without clearly limiting when this skill should be selected. Over-broad routing can cause the agent to invoke this skill in inappropriate contexts, leading to irrelevant guidance, prompt-scope confusion, or accidental overshadowing of more specialized skills.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The keyword list includes generic terms such as 'openapi', 'swagger', 'api documentation', and 'rest api' without qualifiers, which increases the chance of accidental triggering on common developer questions. In an agentic environment, this can misroute user intent and reduce safety and reliability by causing the wrong capability to activate too often.

Vague Triggers

Low

Confidence: 84% confidence
Finding: The example trigger sentences are malformed and do not clearly show what a valid invocation looks like, which weakens routing precision and increases ambiguity in skill selection. While lower impact than the broad trigger issues, unclear examples can still contribute to unintended activation or failure to activate when appropriate.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The skill description uses broad topic-based triggers such as software-and-data, openapi, swagger, api documentation, and rest api without clear narrowing conditions. This can cause the skill to activate for loosely related requests, increasing the chance of unintended invocation, irrelevant guidance, or interference with more appropriate skills, though it does not directly create code-execution or data-exfiltration risk.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger section lists generic keywords and example phrases but does not define scope boundaries or exclusions. This ambiguity makes accidental activation more likely in normal developer conversations about APIs, which can degrade routing accuracy and produce contextually inappropriate outputs.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The skill enables implicit invocation, but the metadata does not define narrow trigger constraints or boundaries for when it should activate. This can cause the agent to invoke the skill in broader contexts than intended, increasing the chance of prompt-surface expansion, unintended data exposure to the skill, or misuse in conversations only loosely related to OpenAPI documentation.

Vague Triggers

High

Confidence: 95% confidence
Finding: The trigger sentence is so broad that it can activate on ordinary help requests that only loosely relate to OpenAPI work. Overbroad activation increases the chance the skill is invoked in unintended contexts, which can cause prompt routing errors, irrelevant instructions, or accidental disclosure of context that should have stayed with another skill.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The phrase 'I need a practical workflow for ...' is a generic request pattern that lacks boundaries on artifact type, API context, or documentation scope. This makes the skill easier to trigger accidentally across many unrelated engineering conversations, reducing routing precision and potentially interfering with safer or more appropriate skills.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.