ClawHub
Back to skill

Security audit

DingTalk OpenAPI Skill

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed DingTalk messaging helper with expected credential use and message-send authority, but users should handle secrets carefully and confirm sends.

Install this only if you want an agent to look up DingTalk users and send DingTalk bot or service-group messages. Use a least-privileged DingTalk app, keep app secrets and access tokens in environment variables or UXC credential storage, avoid pasting real secrets into shared terminals, confirm every send operation, and consider reviewing or pinning the OpenAPI schema before linking the CLI.

SkillSpector

By NVIDIA
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 (1)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The manual token bootstrap example shows users placing an app secret directly into a curl command body, which is sensitive because shell history, process inspection, logs, screenshots, and copied examples can expose the credential. In a documentation context this is not overtly malicious, but it normalizes unsafe secret-handling practices without a strong warning or safer default.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.