Back to skill

Security audit

Feishu Wiki Writer

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent Feishu document-writing guide, but its main creation example hard-codes a real-looking Feishu workspace ID that could send user content to the wrong knowledge base.

Review before installing if you use multiple Feishu workspaces or handle sensitive content. Replace the hard-coded space_id with an explicit user-confirmed target, verify the parent node before creation, and confirm document tokens before any full-document write.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:38
Finding

Hard-Coded Feishu Workspace Identifier May Redirect Document Writes

Content
View full analysis
Remediation
View remediation
", "parent_node_token": "", "title": "", "obj_type": "docx" } ``` 2. Require `space_id` and `parent_node_token` to be obtained from explicit user input or a trusted Feishu lookup operation. 3. Before document creation, display or verify the resolved workspace and parent-node identity, particularly when the document contains sensitive material. 4. Refuse to proceed when destination placeholders remain unresolved. 5. Clearly label all identifiers in examples as synthetic and non-operational. 6. After creation, verify that the returned document belongs to the intended workspace before writing content. 7. For full-document replacement operations, confirm the target document token and preserve a recoverable prior revision where supported. ]]>
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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This markdown file contains user-facing activation text and operational guidance entirely in Chinese, which effectively forces a specific language for use of the skill. The policy allows language constraints only when the skill offers user choice or clearly documents a justified region- or locale-specific limitation, which is not present here.

Content

No source excerpt is available for this finding.