Security audit

AI短信发送工具

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it advertises: it sends template SMS messages through Chuanglan, but users should protect the SMS credentials and treat sends as real external messages that may cost money.

Install only if you intend to let OpenClaw send real SMS through your Chuanglan account. Prefer OpenClaw or OS secret storage over a plaintext .env file, restrict access to any credential file, avoid putting secrets or regulated personal data in template variables, verify CHANGLAN_API_URL before use, and require human review for bulk sends.

SkillSpector

Vulnerability Patterns

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

Findings (2)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The usage documentation explains sending SMS messages but does not clearly warn that phone numbers and template variables will be transmitted to the Chuanglan third-party service. This can lead users to unknowingly send personal data or sensitive content off-platform, creating privacy, compliance, and data-handling risks.

Missing User Warnings

Medium

Confidence: 96% confidence
Finding: The credential setup instructions recommend storing the API password in environment variables or a local .env file in plaintext without any accompanying warning about filesystem permissions, secret management, or leakage risks. This increases the chance that credentials are exposed through shell history, backups, logs, shared machines, or accidental file disclosure, enabling unauthorized SMS sending and account abuse.

Static analysis

No suspicious patterns detected.