Back to skill

Security audit

Feishu Wiki Doc Pipeline/飞书文档导入优化

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent and not malicious, but it asks users to pre-authorize persistent Feishu download and read scopes beyond what every task needs.

Install only if you are comfortable granting Feishu/Lark document read and file download permissions to lark-cli. Prefer authorizing scopes only when the specific task needs them, download into a dedicated folder, and review how to revoke Feishu/Lark authorization after use.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:158
Finding

Persistent Blanket Authorization Exceeds Least-Privilege Requirements

Content
View full analysis
" --as user ``` is consistent with the declared document-reading functionality. It sends the document token to the expected Feishu/Lark service through `lark-cli`; ...[truncated 1868 chars]
Remediation
View remediation
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 (4)

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · README.md (reported line 1)May include surrounding context.

md
---
name: feishu-doc-pipeline
display_name: Feishu Wiki Doc Pipeline
slug: feishu-doc-pipeline

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 1)May include surrounding context.

md
---
name: feishu-doc-pipeline
display_name: Feishu Wiki Doc Pipeline
slug: feishu-doc-pipeline

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The README explicitly frames the skill as downloading attachments to the local disk but does not warn that it will write files onto the user's machine, potentially consuming storage or placing untrusted content locally. In a skill context, missing disclosure around local file writes can lead users to authorize or run actions without understanding that remote content will be persisted to disk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
60% confidence
Finding

A language/locale policy issue applies when a skill forces a specific language without user opt-in. This file is bilingual rather than explicitly forcing one language, but it also does not state that users may choose their preferred language for interaction or output.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.