Back to skill

Security audit

飞书知识库 AI 管家

Security checks for vulnerabilities and agentic risk

Overview

This is a Feishu Wiki management instruction pack with disclosed read and structural edit actions, plus confirmation requirements before changes.

Before installing, be aware that this skill can browse and reorganize Feishu Wiki nodes when paired with the Feishu Wiki tool. Confirm the target space and node list carefully before approving create, move, or rename operations; permission changes are not actually implemented despite one broad description phrase.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The top-level description says the skill supports "权限管理" (permission management), which implies managing access controls. Later, the limitations section states "不能设置权限(那是 feishu_perm 的工作)", directly contradicting that stated capability rather than merely omitting detail.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger terms are broad enough to capture generic knowledge-management or document-organization requests that may not actually be intended for Feishu Wiki. In an agentic environment, overbroad activation can cause the wrong skill to engage and perform read or write operations against a user's Feishu knowledge base without sufficiently specific intent confirmation.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The activation conditions are phrased broadly enough to overlap with ordinary document-organization requests, making accidental or inappropriate skill invocation more likely. Because this skill supports structural operations like create, move, and rename, mistaken activation could lead to unintended modifications in a Feishu Wiki environment if user intent is not tightly verified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

The entire skill instruction set, including description, workflow, and operating principles, is specified only in Chinese, with no indication that users may choose another language. Under the language/locale policy, a skill should not force a specific language unless the constraint is explicit and justified or the user is given a choice.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

The limitations state the skill cannot set permissions, while the earlier description presents permission management as part of the skill's supported operations. This is an intent-level contradiction in the documentation that could mislead users or downstream agents about whether access-control actions are in scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file presents all user-facing guidance exclusively in Chinese, and there is no indication that the skill is region-specific or that users can opt into another language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.