Back to skill

Security audit

Feishu Cli Doc Guide

Security checks for vulnerabilities and agentic risk

Overview

This is a read-only Feishu Markdown compatibility guide with no code execution, persistence, credential handling, or hidden high-impact behavior found.

Installers should understand that this skill is mainly a Chinese-language reference for Feishu Markdown compatibility. Treat the local ~/.claude/rules style-guide reference as optional unless you intentionally maintain that file, and rely on the packaged guidance when reviewing behavior.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (5)

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

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

Content

Scanner excerpt · references/mermaid-spec.md (reported line 91)May include surrounding context.

常见错误与修复

Rendering diagram...

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

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

Content

Scanner excerpt · references/mermaid-spec.md (reported line 91)May include surrounding context.

常见错误与修复

Rendering diagram...

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description and the entire skill guide are written only in Chinese, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking or region-specific audience. This creates a natural-language policy concern because the file effectively imposes a language constraint without opt-in or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The title and opening description present the specification entirely as a Chinese-language standard for Mermaid usage, and the rest of the document consistently instructs in Chinese without any opt-in, alternative locale, or justification that this must be Chinese-only. Under the language/locale policy, forcing a specific language without user choice is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The manifest describes this skill as a Feishu Markdown compatibility specification covering Mermaid, tables, callouts, formulas, images, and API fault tolerance before import. Line L555 directs users to ~/.claude/rules/markdown-style-guide.md, which is a separate local rules source and not part of the declared compatibility guide scope, introducing an external dependency unrelated to the stated purpose of this file itself.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.