Feishu Doc Writing

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:16 PM UTC
• Version:
  1.0.0

Overview

This is a simple Feishu document-writing guide with disclosed formatting and sharing defaults, not executable behavior.

Safe to install as a writing aid. Before allowing an agent to create or share a Feishu document, confirm the intended recipients, who counts as the boss or group members, and whether any external-facing version needs additional redaction.

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 (1)

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The trigger condition is broad enough to match many ordinary requests involving meeting notes, chat summaries, or research writeups, which increases the chance the skill activates when the user did not explicitly intend to use it. Mis-triggering can cause unintended formatting, document creation behaviors, or application of preset permission rules in contexts where they are inappropriate.

VirusTotal

66/66 vendors flagged this skill as clean.