Back to skill

Security audit

Feishu Wiki Andy27725

Security checks for vulnerabilities and agentic risk

Overview

This Feishu wiki skill is mostly coherent, but it can modify shared wiki/document content and its instructions do not clearly require explicit confirmation before those changes.

Install only if you expect the agent to manage Feishu wiki content, not just browse it. Prefer read-only wiki permissions where possible, and require the agent to confirm the exact space, node, document, and intended change before creating, moving, renaming, or writing pages.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The activation text uses generic phrases like 'knowledge base', 'wiki', or 'wiki links', which are common in ordinary conversation and can cause over-broad skill activation. In a write-capable integration, unintended activation increases the chance the agent will access or modify Feishu content when the user did not explicitly intend to invoke this tool.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill documents state-changing operations across both wiki and dependent document tools, including create, move, rename, and write flows, but provides no warning, confirmation gate, or scope limitation for modifying user content. Because the skill explicitly instructs a workflow from wiki navigation to document write operations, accidental or prompt-induced misuse could lead to unauthorized content edits, renames, or reorganization of knowledge base data.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.