飞书@机器人

• Outcome: Pass
• Latest audit: May 28, 2026, 11:30 AM
• Version:
  1.0.0

Overview

This is an instruction-only Feishu bot mention helper; its credential and chat-history examples match the stated purpose but need careful handling.

Install only if you want an agent to help send Feishu group messages that mention bots. Use a least-privilege Feishu app, keep app_secret and tenant tokens out of logs and shared files, confirm CHAT_ID and open_id before sending, and avoid message-history queries in sensitive chats unless you have authorization.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 83% confidence
• Finding: The skill explicitly instructs users to obtain a tenant access token with app credentials and query group message history to extract mentions, but it does not warn that this accesses potentially sensitive chat content and requires privileged credentials. In an agent-skill context, normalizing credential use and chat-history scraping without consent, scoping, or data-handling guidance increases the risk of unauthorized data access and privacy violations.

VirusTotal

65/65 vendors flagged this skill as clean.