Feishu Doc Workflow

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:20 PM UTC
• Version:
  1.0.0

Overview

This instruction-only Feishu document workflow is coherent and disclosed, but its public-link sharing steps should be used carefully.

Install only if you want an agent to edit Feishu documents and, when asked, make them publicly readable by link. Before using the public-sharing step, verify the exact document and confirm it contains no confidential, internal, personal, or regulated data; prefer narrower Feishu sharing when public access is not necessary.

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: 92% confidence
• Finding: The skill explicitly instructs changing Feishu document permissions to internet-readable settings such as `external_access_entity = open` and `link_share_entity = anyone_readable` without requiring a privacy warning, confirmation of data sensitivity, or a least-privilege check. This can cause accidental public exposure of internal or confidential documents if the workflow is used on the wrong file or followed mechanically.

VirusTotal

66/66 vendors flagged this skill as clean.