Security audit

AnyGen图表生成-免费版

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AnyGen CLI wrapper for generating diagrams through a remote rendering service, with expected authentication and command-line use.

Before installing, confirm you are comfortable using the AnyGen CLI, authenticating with an API key or browser login, and sending diagram descriptions to AnyGen's remote service. Avoid including secrets, regulated data, or confidential architecture details unless your organization approves that service.

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Context-Inappropriate Capability

Low

Confidence: 80% confidence
Finding: The skill requests browser access beyond its core rendering purpose, which expands the attack surface and gives the skill an additional channel for navigation, authentication, and potential data exposure. Because browser-based auth is optional rather than essential to diagram generation, granting browser permissions by default violates least privilege and could enable unintended external interactions if the skill is invoked automatically.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill relies on an external API/service and browser or CLI authentication, but it does not clearly warn that user prompts and diagram descriptions are transmitted to a remote service. This is dangerous because users may enter sensitive architecture, business, or personal information under the assumption of local processing, resulting in unintended disclosure to a third party.

Static analysis

No suspicious patterns detected.