Back to skill

Security audit

飞书文档智能转换Markdown

Security checks across malware telemetry and agentic risk

Overview

This Feishu-to-Markdown skill appears purpose-aligned, but it can automatically copy private document contents into local archives and knowledge-base files with limited user control.

Review this before installing if you handle confidential Feishu documents. Use it only where local archiving is acceptable, set a safe output directory, disable or avoid knowledge-base sync unless intended, and verify the Feishu plugin permissions and any generated LEARNINGS.md entries before committing or sharing the output.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The README advertises automatic archiving, local output, and knowledge-base syncing of converted Feishu documents, but it does not warn users that the content may include sensitive internal data and may be copied into new storage locations. For a document-conversion skill operating on private enterprise documents, undocumented persistence and replication behavior increases the risk of unintended data disclosure, over-retention, and syncing sensitive content into broader repositories.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill states it will automatically archive converted documents and write summaries/core points into a knowledge base, but it does not require an explicit user confirmation before modifying local files or shared knowledge artifacts. This can lead to unintended persistence of sensitive Feishu content, accidental data propagation, and silent contamination of internal knowledge stores.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill describes fetching complete Feishu document content and metadata via API, including potentially private resources, without clearly warning the user about network access, privacy implications, or handling of sensitive content. In this context, the skill is specifically designed to process private enterprise documents, so omission of consent and disclosure meaningfully increases the risk of over-collection and unintended exposure.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.