ClawHub
Back to skill

Security audit

Yuboto Omni API Assistant

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Yuboto/Octapush messaging API helper, but users should treat SMS sending, callbacks, API keys, and local logs as sensitive.

Install only if you intend to let OpenClaw work with a real Yuboto/Octapush account. Confirm recipients, sender, message text, CSV files, batch size, and cost before sending; do not put API keys in URLs; use only trusted HTTPS callback/base URLs; keep full payload persistence disabled unless needed; and rotate the API key if it is ever exposed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding
The skill declares operational capabilities that include environment-variable access, file read/write, and network use, but does not declare corresponding permissions. This creates a transparency and governance gap: the skill can handle sensitive data and persist or transmit it without an explicit permission boundary, increasing the chance of unintended secret exposure or misuse in agent runtimes that rely on declared permissions for policy enforcement.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The documentation explicitly endorses passing the API key as a GET parameter (`apiKey`) in request URLs. Credentials in URLs are commonly exposed through browser history, server/access logs, monitoring systems, referrer headers, shared screenshots, and proxy infrastructure, so integrators following this guidance may unintentionally leak long-lived API secrets.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The callback design and examples place message metadata, user replies, and file download links into GET query strings. Query strings are routinely logged and propagated across infrastructure, so this can expose user content, phone numbers, message IDs, and downloadable file links to parties that should not receive them.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The SSO section documents direct username/password token retrieval but does not include guidance on secure credential handling, storage, transport, or secret redaction. This can lead downstream implementers to embed account credentials in code, logs, or insecure automation, increasing credential theft risk.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
references/omni_api_v1_10_raw.md:356