Back to skill

Security audit

飞书文档智能转换Markdown

Security checks for vulnerabilities and agentic risk

Overview

This skill converts user-provided Feishu documents to Markdown and clearly describes local archiving and optional knowledge-base sync, though users should treat converted files as persistent copies of sensitive source content.

Before installing, confirm you are comfortable with full Feishu document contents and metadata being fetched, converted, and saved locally, including raw backups and summaries. Use the output path and auto_archive or auto_sync settings carefully for confidential documents, and only enable knowledge-base sync when the destination permissions and retention are acceptable.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The README advertises automatic classification, archiving, and knowledge association features that go beyond straightforward document-to-Markdown conversion. This expands the skill's effective data-handling scope and can cause users to expose document contents to additional storage or organizational systems they may not expect, increasing confidentiality and governance risk.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

Documented automatic synchronization to a knowledge base exceeds the narrow conversion-focused description and implies onward movement of potentially sensitive document contents. Even if intended as a convenience feature, undocumented or under-described sync behavior can lead to unexpected data propagation and permission boundary violations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README instructs users to sync converted content to a knowledge base without any warning about privacy, data transmission, or access implications. Because Feishu documents can contain sensitive internal information, silent synchronization materially raises the risk of unintended disclosure, over-sharing, or compliance issues.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

Configuration options for auto-archive and knowledge-base sync show persistent storage and secondary distribution behaviors not reflected in the core description. Hidden or insufficiently disclosed persistence features are dangerous because converted documents may contain confidential business data that users expect to remain local and transient.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly states it will automatically archive converted documents into dated project folders and write summaries and key points into LEARNINGS.md, but it does not warn the user that invoking the skill causes persistent data writes and broader redistribution of source content. This is dangerous because users may supply sensitive Feishu documents expecting a one-time conversion, while the skill silently creates additional copies and knowledge-base artifacts that expand retention and exposure.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The processing flow says the skill fetches the complete Feishu document content and metadata via API, but the description does not include a privacy warning or limits on what may be collected. This is risky because users may not realize the full document body, embedded context, and metadata such as project/domain classification are being retrieved and subsequently processed, stored, or reused beyond the immediate conversion task.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

Automatic classification and archival imply that converted content will be written to storage, but the README does not prominently warn users about local persistence. While lower impact than external sync, this can still create residual sensitive data on disk that users did not intend to retain.

Content

No source excerpt is available for this finding.