Feishu Sheets (Fixed)

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:24 PM UTC
• Version:
  1.0.1

Overview

This skill does what it says: it connects to Feishu Sheets to create, read, edit, append, and delete spreadsheet content, with no hidden persistence or unrelated behavior found.

Install this only for workflows where the agent should be allowed to access Feishu Sheets. Use a dedicated Feishu app with the narrowest scopes needed, prefer read-only credentials when editing is not required, and confirm spreadsheet tokens, sheet IDs, ranges, and delete actions before allowing writes or deletions.

SkillSpector

By NVIDIA

Vulnerability Patterns

• 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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill documents destructive operations such as write, append, delete_dimension, and delete_sheet without any warning, confirmation requirement, or guidance on safe use. In an agent context, this increases the chance of accidental or prompt-induced modification or deletion of business data, especially because spreadsheet tokens and sheet IDs are sufficient to target existing documents.

VirusTotal

65/65 vendors flagged this skill as clean.