Feishu New Chat

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:17 PM UTC
• Version:
  0.1.2

Overview

This is a narrowly scoped Feishu helper that can post topics as the user, and that posting behavior is clearly disclosed and bounded by user intent checks.

Install this only if you want the assistant to create Feishu topic-group posts for you. Before sending in shared or sensitive groups, verify the destination group, message text, @mentions, and any carried-over context because messages are posted as you and remain in Feishu.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The skill description contains broad natural-language triggers such as “开话题”, “开个新话题”, and requests to simulate a new chat workflow, which can overlap with ordinary conversation. Because this skill sends messages as the user, ambiguous activation increases the risk of unintended message posting to Feishu if the orchestrator uses description matching too loosely.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The parsing guidance treats many freeform phrases as likely triggers, including context-carryover and follow-up wording that may naturally appear in normal chats. In a skill that can post as the user, this broad trigger surface makes accidental activation and unintended outbound messaging materially more likely.

VirusTotal

66/66 vendors flagged this skill as clean.