飞书文档管理器Pro

• Outcome: Review
• Latest audit: May 29, 2026 at 9:26 PM UTC
• Version:
  1.0.0

Overview

This Feishu document skill appears purpose-aligned, but it gives agents examples for clearing or overwriting documents without strong user-confirmation safeguards.

Install only if you are comfortable giving the agent authenticated Feishu document write authority. Before using destructive examples, require the agent to restate the document ID, show what will be deleted or replaced, and get explicit confirmation; prefer append or targeted updates unless full replacement is intentional. VirusTotal was pending and was not used as negative evidence.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• 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 (3)

Context-Inappropriate Capability

Medium

• Confidence: 91% confidence
• Finding: The weather-update example expands the skill beyond Feishu document management by invoking an unrelated external service (wttr.in) and then injecting that data into a document. This increases the attack surface and creates an unnecessary data-flow from an external source into enterprise documents without documenting trust, validation, or consent boundaries.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill provides direct instructions for bulk block deletion and document clearing but does not prominently warn that these actions are destructive and may irreversibly remove existing content. In an agent context, this omission makes accidental data loss more likely because deletion is normalized as a routine operation without requiring explicit confirmation safeguards.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The example workflow clears the entire document before writing new content, but it does not warn that running it will overwrite all existing data in the target document. This is dangerous because users may treat it as a harmless update example and unintentionally destroy production content.

VirusTotal

65/65 vendors flagged this skill as clean.