Security audit

Api Doc Generator Free

Security checks across malware telemetry and agentic risk

Overview

This skill is mostly an API documentation generator, but it asks for broad command-execution capability and includes unclear credential and network-diagnostic guidance that users should review before installing.

Review this skill before installing. It appears intended to generate API docs, but you should avoid giving it real secrets, require confirmation before any shell or network command, and prefer a version without exec unless you specifically need command-line diagnostics.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (7)

Intent-Code Divergence

Medium

Confidence: 95% confidence
Finding: The skill gives contradictory guidance about credentials: it states no API key is required, then later instructs users to export an API key as an environment variable. This can mislead users into unnecessarily exposing secrets to the agent/runtime or normalizing credential handling where it is not needed, increasing the chance of accidental disclosure or misuse.

Context-Inappropriate Capability

Medium

Confidence: 90% confidence
Finding: The error-handling section instructs users to run network-diagnostic commands such as ping and troubleshoot firewall/proxy settings, which is unrelated to simple API document generation. Encouraging shell/network operations expands the skill's operational scope and can cause unnecessary command execution, environment probing, or outbound network activity in contexts where only text transformation should occur.

Context-Inappropriate Capability

Low

Confidence: 88% confidence
Finding: The manifest grants broad exec capability even though the documented functionality is primarily generating OpenAPI and Markdown from provided text. Unnecessary exec access violates least privilege and increases the blast radius if the skill is misused, prompt-injected, or accidentally invoked with sensitive workspace context.

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The activation wording is broad ('Use when 需要API集成、接口对接、Webhook配置、系统连接时使用') and not tightly constrained to documentation generation. Overbroad triggers can cause unintended invocation in unrelated integration tasks, exposing the skill's write/exec capabilities in contexts where the user did not intend to use it.

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The scenario keyword coverage list is excessively broad and includes many generic phrases, increasing the chance the platform auto-selects this skill for loosely related prompts. Because the skill also has write and exec capabilities, accidental invocation raises the risk of unnecessary file modification or command execution.

Missing User Warnings

Medium

Confidence: 84% confidence
Finding: The skill advertises exec capability but does not clearly warn users that command execution may occur or explain under what circumstances. Lack of disclosure undermines informed consent and can lead users to provide inputs assuming a safe text-only operation when the skill can actually execute shell commands.

Missing User Warnings

Low

Confidence: 80% confidence
Finding: The documentation tells users to configure an API key via environment variable but does not warn that credentials are sensitive or should not be echoed, logged, or pasted into prompts. This increases the risk of accidental secret exposure during troubleshooting or agent-assisted setup.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.