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 or Swagger documentation assistance. Users should be aware it may activate for some broad developer-experience or software-data prompts, so ambiguous requests may need clarification or manual skill selection.

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 (8)

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger phrases are generic and malformed enough that they could match loosely related requests, causing unintended skill activation. In an agent environment, over-broad invocation increases the chance that this skill runs in contexts it was not designed for, which can misroute user intent and produce irrelevant or unsafe automated actions.

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The trigger phrases are broad, repetitive, and partially malformed, which can cause the skill to activate for vague requests unrelated to the user's actual intent. In an agent environment, overbroad activation increases the chance of inappropriate routing or unintended execution of this skill on untrusted prompts, expanding the attack surface for prompt-injection or workflow confusion.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The trigger keywords include broad terms such as 'software-and-data' and 'developer experience', which can overlap with many unrelated requests and cause the skill to activate outside its intended scope. In an agent system, overly broad routing can expose users to irrelevant instructions, accidental tool selection, or mis-scoped automation, increasing the chance of downstream mistakes.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The skill description and use conditions are broad enough that it could activate for generic software or documentation-related requests without clear boundaries. Unintended invocation can cause the agent to apply this skill in the wrong context, leading to irrelevant guidance, prompt-surface expansion, or interference with more appropriate skills.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The keyword list contains very generic triggers such as 'software-and-data' and 'developer experience' without any guardrails. These terms are likely to match many unrelated requests, increasing the chance of accidental skill activation and misrouting user interactions.

Vague Triggers

Low

Confidence: 86% confidence
Finding: The example trigger phrases show invocation patterns but do not define when the skill should not activate. This ambiguity can reinforce overbroad matching behavior and make operators or downstream systems treat vague prompts as valid triggers.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The skill enables implicit invocation while using a very broad default prompt and description, which can cause the agent to auto-select this skill for ordinary requests without clear user intent or tight routing boundaries. This creates an over-broad activation surface that may lead to unintended data exposure, incorrect tool use, or prompt-routing abuse, especially if the skill is invoked in contexts only loosely related to OpenAPI documentation.

Vague Triggers

High

Confidence: 95% confidence
Finding: The trigger sentences are so broad and awkwardly templated that they can match ordinary user requests about help or practical workflows, causing the skill to activate outside its intended scope. Over-broad activation can route unrelated conversations into this skill, increasing the chance of incorrect guidance, prompt-scope confusion, or unintended handling of user content.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.