feishu-dingtalk-bridge

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Feishu/DingTalk workflow helper, but it requires sensitive enterprise access tokens that users must handle carefully.

Install only if you intend to let an agent work with Feishu or DingTalk enterprise data. Use a least-privilege app token, provide it through a secure secret mechanism where possible, avoid pasting real tokens into shared chats or repos, and confirm tokens are masked in logs and outputs.

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 (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The README instructs users to obtain and pass high-privilege Feishu/DingTalk access tokens directly in skill inputs, but provides no warning about secure storage, redaction, least-privilege scopes, or log exposure. In an agent or workflow environment, this increases the chance that credentials are pasted into prompts, config files, screenshots, or telemetry and then reused to access enterprise calendars, approvals, and documents.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly requests an `auth_token` and processes enterprise calendar, approval, document, and task data, but it provides no clear warning about credential handling, data scope, retention, or privacy risks. In an agent ecosystem, this omission can cause users to paste high-privilege tokens and sensitive business context into a third-party skill without understanding exposure or least-privilege requirements.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal